Upload
others
View
2
Download
0
Embed Size (px)
Citation preview
Talsyntes: Joakim Gustafson
Tal, musik och hörsel
1
J. Gustafson, CTT, KTH
Speech synthesisSpeech synthesisSpeech synthesisSpeech synthesis
DT2112DT2112DT2112DT2112
JoakimJoakimJoakimJoakim Gustafson, CTT, KTHGustafson, CTT, KTHGustafson, CTT, KTHGustafson, CTT, KTH
School for Computer Science and CommunicationSchool for Computer Science and CommunicationSchool for Computer Science and CommunicationSchool for Computer Science and CommunicationMany slides prepared by Many slides prepared by Many slides prepared by Many slides prepared by OlovOlovOlovOlov EngwallEngwallEngwallEngwall (and others)(and others)(and others)(and others)
J. Gustafson, CTT, KTH 2
TextTextTextText----ToToToTo----SpeechSpeechSpeechSpeech synthesissynthesissynthesissynthesis (TTS)(TTS)(TTS)(TTS)
The automatic generation of synthesized sound or
visual output from any phonetic string.
Our focus in this course!
J. Gustafson, CTT, KTH 3
Different kinds of speech synthesisDifferent kinds of speech synthesisDifferent kinds of speech synthesisDifferent kinds of speech synthesis
• Recorded speech
– Words or phrases (telephone banking)
– Fixed vocabulary – maintenance problems…
• Concatenative speech synthesis
• Parametric synthesis
• Multimodal synthesis
J. Gustafson, CTT, KTH 4
WhatWhatWhatWhat a a a a synthesisersynthesisersynthesisersynthesiser is to is to is to is to conveyconveyconveyconvey
• The linguistic component: semantic information that is part of the speaker’s language (e.g. question intonation)
• The paralinguistic component: the speaker’s attitudinal or emotional states, sociolect and regional dialect.
• The extralinguistic component: the individuality, gender and age of a certain speaker. It can be judged independently of the language.
To adapt a speech synthesizer to a certain speaker, we need both the para- and extralinguisitic components.
J. Gustafson, CTT, KTH
Desireable synthesis features Desireable synthesis features Desireable synthesis features Desireable synthesis features from a dialogue perspectivefrom a dialogue perspectivefrom a dialogue perspectivefrom a dialogue perspective
• Real-time, Incremental, Interruptable
• Explicit control of prosodic parameters– Fundamental frequency
– Intensity
– Natural sounding lengthening, hesitation, interruptions
• Generation of extra-linguistic sounds– Filled pauses
– Creeks/Gargles
– Smacks/Inhalations/exhalations to give turn
J. Gustafson, CTT, KTH 6
The synthesis spaceThe synthesis spaceThe synthesis spaceThe synthesis space
Intelligibility
Naturalness
Bit rate
Vocabulary
Units
Complexity
Processingneeds
Flexibility
SpeechKnowledge
Cost
Talsyntes: Joakim Gustafson
Tal, musik och hörsel
2
J. Gustafson, CTT, KTH 7
The steps in TTSThe steps in TTSThe steps in TTSThe steps in TTS
text
Linguistic analysis
Prosodic analysis
Phonetic description
Sound generation
Morphological analysisLexicon and rulesSyntax analysis
Rules and lexicon
Rules and unit selection
Concatenation Rules
Language ident.
“abcd”
J. Gustafson, CTT, KTH
The automatic generation of synthesized sound from any text string.
From textFrom textFrom textFrom text
J. Gustafson, CTT, KTH 9
PPPPreprocessorreprocessorreprocessorreprocessor
• Sentence end detection Sentence end detection Sentence end detection Sentence end detection (semicolon, period – ratio, time and
decimal point, sentence ending respectively)
• AbbreviationsAbbreviationsAbbreviationsAbbreviations (e.g. – for instance)
Changed to their full form with the help of lexicons
• AcronymsAcronymsAcronymsAcronyms (I.B.M – these can be read as a sequence of characters, or
NASA which can be read following the default way)
• NumbersNumbersNumbersNumbers (Once detected, first interpreted as rational, time of the
day, dates and ordinal depending on their context)
• IdiomsIdiomsIdiomsIdioms (e.g. “In spite of”, “as a matter of fact”– these are combined
into single FSU using a special lexicon)
J. Gustafson, CTT, KTH 10
GraphemeGraphemeGraphemeGrapheme----totototo----phonemephonemephonemephoneme conversionconversionconversionconversion
• Dictionary:– Store a maximum of phonological knowledge into a lexicon.
– Compounding rules describe how the morphemes of dictionary items are modified.
– Hand-corrected, expensive– The lexicon is never complete: needs out of vocabulary pronouncer,
transcribed by rule.
• Rules:– A set of letter to sound (grapheme to phoneme) rules.
– Words pronounced in a such a particular way that they have their own rule are stored in exceptions directory.
– Fast & easy, but lower accuracy
• Machine learning:– Cart tree– Analogy pronunciation
J. Gustafson, CTT, KTH
11111111
ProsodyProsodyProsodyProsody
• Prosody = melody, rhythm, “tone” of speech
• Not what words are said, but how they are said
• Prosody is conveyed using:– Pitch– Phone durations– Energy
• Human languages use prosody to convey:
– phrasing and structure (e.g. sentence boundaries)
– disfluencies (e.g. false starts, repairs, fillers)
– sentence mode (statement vs question)
– emotional attitudes (urgency, surprise, anger)
J. Gustafson, CTT, KTH 12
Intonation: F0 contourIntonation: F0 contourIntonation: F0 contourIntonation: F0 contourLarge pitch range (female)Authoritive (final fall)Emphasis for Finance (H*)Final has a raise – more information to come
• Word stress and sentence intonation
– each word has at least one syllable which is spoken with higher prominence
– in each phrase the stressed syllable can be accented depending on the semantics and syntax of the phrase
• Prosody relies on syntax, semantics, pragmatics: personal reflection of the reader.
Talsyntes: Joakim Gustafson
Tal, musik och hörsel
3
J. Gustafson, CTT, KTH 13
Pitch contour modelingPitch contour modelingPitch contour modelingPitch contour modeling
• Tonetics (the British school)– tone groups composed of syllables {unstressed, stressed, accented
or nuclear}.
– nuclear syllables have nuclear tones {fall, rise, fall-rise, rise-fall}
• ToBI (Tones and Break Indices)– Phrases split into intermediate phrases composed of syllables.
– Relative tone levels: high (H) or low (L) (plus diacritics) at every intonational or intermediate phrase boundary (%) and on every accented syllable
• Stylization method (prosodic pattern measured from natural speech)– Demo
J. Gustafson, CTT, KTH
The automatic generation of synthesized sound from any text string.
To SpeechTo SpeechTo SpeechTo Speech
J. Gustafson, CTT, KTH 15
SynthesisSynthesisSynthesisSynthesis approachesapproachesapproachesapproaches
By ConcatenationBy ConcatenationBy ConcatenationBy ConcatenationElementary speech units are stored in a database and then concatenated and processed to produce the speech signal
By RuleBy RuleBy RuleBy RuleSpeech is produced by mathematical rules that describe the influence of phonemes on one another
J. Gustafson, CTT, KTH
Research trends in Research trends in Research trends in Research trends in speech synthesisspeech synthesisspeech synthesisspeech synthesis
1950 Synthesis by analysis
1960 Phonetic rules
1970 Linguistic processing
1980 Concatenation
1990 Automatic procedures
2000
J. Gustafson, CTT, KTH
TextTextTextText----totototo----Speech Speech Speech Speech Synthesis EvolutionSynthesis EvolutionSynthesis EvolutionSynthesis Evolution
1962 1967 1972 1982 1987 1992 1997 2002
Year
Formant
Synthesis
Bell Labs; Joint
Speech Research
Unit; MIT (DEC-
Talk); Haskins
Lab; KTH
LPC-Based
Diphone/Dyad
Synthesis
Bell Labs; CNET;
Bellcore; Berkeley
Speech
Technology
Unit Selection
Synthesis
ATR in Japan; CSTR
in Scotland; BT in
England; AT&T Labs
(1998); L&H in
Belgium
Poor
Intelligibility;
Poor Naturalness,
Small footprint
Good
Intelligibility;
Poor Naturalness
Good
Intelligibility;
Customer Quality
Naturalness
(Limited Context)
HMM
Synthesis
HTS in Japan; CSTR
in Scotland;
Multi-speaker
training, speaker
adaptation;
Naturalness,
generative, Small
footprint
J. Gustafson, CTT, KTH 18
Synthesis by ruleSynthesis by ruleSynthesis by ruleSynthesis by rule
Talsyntes: Joakim Gustafson
Tal, musik och hörsel
4
J. Gustafson, CTT, KTH
ArticulatoryArticulatoryArticulatoryArticulatory SynthesisSynthesisSynthesisSynthesis
J. Gustafson, CTT, KTH 20
ArticulatoryArticulatoryArticulatoryArticulatory synthesissynthesissynthesissynthesispotential usepotential usepotential usepotential use
• Articulatory synthesis– Calculations directly from cross
sectional areas
– Fluid dynamics calculations
• Visual synthesis– Articulation training
• Demonstrations and research
J. Gustafson, CTT, KTH 21
ArticulatoryArticulatoryArticulatoryArticulatory parametersparametersparametersparameters
• Jaw opening
• Lip rounding
• Lip Protrusion
• Tongue position
• Tongue height
• Tongue tip
• Velum
• Hyoid
J. Gustafson, CTT, KTH
From articulation to acousticsFrom articulation to acousticsFrom articulation to acousticsFrom articulation to acoustics
Transfer function
Vocal tract model
Tubes
Waveform
Cross-sections
3D air flow calculations
Area function
J. Gustafson, CTT, KTH
Benefits:Benefits:Benefits:Benefits:• Speech production in the same way as humans• Can be made with few parameters• The changes are intuitive
(raise the tongue tip, round the lips)
Disadvantages:Disadvantages:Disadvantages:Disadvantages:• Computationally demanding• Problems with consonants• Articulatory measurements required• State-of-the-art articulatory synthesis still sounds bad
Summary: Summary: Summary: Summary: ArticulatoryArticulatoryArticulatoryArticulatory SynthesisSynthesisSynthesisSynthesis
J. Gustafson, CTT, KTH
Formant SynthesisFormant SynthesisFormant SynthesisFormant Synthesis
Talsyntes: Joakim Gustafson
Tal, musik och hörsel
5
J. Gustafson, CTT, KTH
Formant synthesis (1959Formant synthesis (1959Formant synthesis (1959Formant synthesis (1959----1987)1987)1987)1987)
• Haskins, 1959
• KTH – Stockholm, 1962
• Bell Labs, 1973
• MIT, 1976
• MIT-talk, 1979
• Speak ‘N spell, 1980
• BELL Labs, 1985
• Dec talk, 1987
J. Gustafson, CTT, KTH 26
• OVE I (1953)
• The original & a new version on the computer + OVE II (1962)
LetLetLetLet usususus taketaketaketake a look at OVEa look at OVEa look at OVEa look at OVE
formant.exe (Command Line)
J. Gustafson, CTT, KTH 27
OVE IIOVE IIOVE IIOVE II
J. Gustafson, CTT, KTH
RuleRuleRuleRule----driven formant synthesisdriven formant synthesisdriven formant synthesisdriven formant synthesis
• Parameters are generated by rule(RULSYS , Carlson et al.)
• Formant values are generated by interpolating between target frequencies
• Parameters are fed to a synthesizer (GLOVE, Carlson et al.)
0 0.1 0.2 0.3 0.4 0.5 0.6 0.7 0.8 0.90
500
1000
1500
2000
2500
3000
3500
4000 M O B I: L sil
J. Gustafson, CTT, KTH
Summary: formant synthesisSummary: formant synthesisSummary: formant synthesisSummary: formant synthesis
Benefits:Benefits:Benefits:Benefits:• Possible to change the voice to get different:
• speakers•emotions•voice qualities
• Small footprint
Disadvantages:Disadvantages:Disadvantages:Disadvantages:• Hard to achieve naturalness in voice source• Some consonant sounds are hard to model with formants (bursts)
J. Gustafson, CTT, KTH 30
From rule based From rule based From rule based From rule based concatenativeconcatenativeconcatenativeconcatenative synthesissynthesissynthesissynthesis
• Rule based sounds unnatural, while concatenative synthesis provides
(piece-wise) high quality speech.
• Certain sounds are hard to be produced by rule but easy to concatenate:
– Bursts, voiceless stops are too difficult
• Rule based had an advantage of small footprint, however storing the
segment database is no longer an issue
• Change of applications:
– From reading machines for the blind to spoken dialogue systems
Talsyntes: Joakim Gustafson
Tal, musik och hörsel
6
J. Gustafson, CTT, KTH 31
SynthesisSynthesisSynthesisSynthesis by by by by concatenationconcatenationconcatenationconcatenation
J. Gustafson, CTT, KTH 32
Let’sLet’sLet’sLet’s get the terms straightget the terms straightget the terms straightget the terms straight
ConcatenativeConcatenativeConcatenativeConcatenative synthesissynthesissynthesissynthesisDefinition: Definition: Definition: Definition: All kinds of synthesis based on the concatenation of units, regardless of
type (sound, formant trajectories, articulatory parameters) and size (diphones, triphones, syllables, longer units). There is only one candidate only one candidate only one candidate only one candidate per setting.
Everyday use: Everyday use: Everyday use: Everyday use: Concatenation of same-size sound units.
Unit selection synthesisUnit selection synthesisUnit selection synthesisUnit selection synthesisDefinition: Definition: Definition: Definition: All kinds of synthesis based on the concatenation of units where there are several candidates several candidates several candidates several candidates to choose from, regardless of if the candidates have the same, fixed size or if the size is variable.
Everyday use: Everyday use: Everyday use: Everyday use: Concatenation of variable sized sound units.
J. Gustafson, CTT, KTH 33
Database preparation when Database preparation when Database preparation when Database preparation when building a building a building a building a concatenativeconcatenativeconcatenativeconcatenative synthesissynthesissynthesissynthesis
• Choose the speech units (Phone, Diphone, Sub-word unit, Cluster based unit selection)
• Compile and record utterances
• Segment signal and extract speech units
• Store segment waveforms (along with context) and information in a database:
Dictionary, waveform, pitch mark
e.g. “ch-l r021 412.035 463.009 518.23”
diphone file Start time Middle time End
• Pitch mark file: a list of each pitch mark position in the file
• Extract parameters; create parametric segment
database (for data compaction and prosody matching)
• Perform amplitude equalization (prevents mismatches)
J. Gustafson, CTT, KTH 34
Signal manipulations in Signal manipulations in Signal manipulations in Signal manipulations in concatenativeconcatenativeconcatenativeconcatenative synthesissynthesissynthesissynthesis
• Prosodic modifications– Possibility to modify F0
– Possibility to lengthen or shorten segments
• Spectral modifications– Interpolation of spectrum at joints
J. Gustafson, CTT, KTH 35
Sequences of a particular sound/phone in all its environmentsof occurrence or all/most two-phone sequences occurring in alanguage: _auto_ -> _a, au, ut, to, o_
• Rationale: the center’ofcenter’ofcenter’ofcenter’of a phonetic realization is the moststablestablestablestable region, whereas the transition from one segment toanother contains the most interesting phenomena, and is thusthe hardest to model.
Assignment: Diphone ”synthesis”; cut and paste
DiphoneDiphoneDiphoneDiphone SynthesisSynthesisSynthesisSynthesis
J. Gustafson, CTT, KTH
DiphonesDiphonesDiphonesDiphones
• Need O(phone2) number of units– Some combinations don’t exist (hopefully)
– ATT (Olive et al. 1998) system had 43 phones
• 1849 possible diphones
• Phonotactics ([h] only occurs before vowels), don’t need to keep diphones across silence
• Only 1172 actual diphones
– May include stress, consonant clusters
• So could have more
– Lots of phonetic knowledge in design
• Database relatively small– Around 8 megabytes for English (16 KHz 16 bit)
Slide from Richard Sproat
Talsyntes: Joakim Gustafson
Tal, musik och hörsel
7
J. Gustafson, CTT, KTH
Building diphone schemataBuilding diphone schemataBuilding diphone schemataBuilding diphone schemata
• Find list of phones in language:– Plus interesting allophones
– Stress, tons, clusters, onset/coda, etc
– Foreign (rare) phones.
• Build carriers for:– Consonant-vowel, vowel-consonant
– Vowel-vowel, consonant-consonant
– Silence-phone, phone-silence
– Other special cases
• Check the output:– List all diphones and justify missing ones
– Every diphone list has mistakes
Slide from Richard Sproat J. Gustafson, CTT, KTH
Designing a diphone inventory:Designing a diphone inventory:Designing a diphone inventory:Designing a diphone inventory:
Nonsense wordsNonsense wordsNonsense wordsNonsense words
• Build set of carrier words:– pau t aa b aa b aa pau– pau t aa m aa m aa pau– pau t aa m iy m aa pau– pau t aa m iy m aa pau– pau t aa m ih m aa pau
• Advantages:– Easy to get all diphones
– Likely to be pronounced consistently• No lexical interference
• Disadvantages:– (possibly) bigger database
– Speaker becomes bored
Slide from Richard Sproat
J. Gustafson, CTT, KTH
Designing a diphone inventory:Designing a diphone inventory:Designing a diphone inventory:Designing a diphone inventory:
Natural wordsNatural wordsNatural wordsNatural words
• Greedily select sentences/words:– Quebecois arguments
– Brouhaha abstractions
– Arkansas arranging
• Advantages:– Will be pronounced naturally
– Easier for speaker to pronounce
– Smaller database? (505 pairs vs. 1345 words)
• Disadvantages:– May not be pronounced correctly
Slide from Richard Sproat J. Gustafson, CTT, KTH
Making recordings consistent:Making recordings consistent:Making recordings consistent:Making recordings consistent:
• Diphone should come from mid-word– Help ensure full articulation
• Performed consistently– Constant pitch (monotone), power, duration
• Use (synthesized) prompts:– Helps avoid pronunciation problems
– Keeps speaker consistent
– Used for alignment in labeling
Slide from Richard Sproat
J. Gustafson, CTT, KTH
Recording conditionsRecording conditionsRecording conditionsRecording conditions
• Ideal:– Anechoic chamber
– Studio quality recording
– EGG signal
• More likely:– Quiet room
– Cheap microphone/sound blaster
– No EGG
– Headmounted microphone
• What we can do:– Repeatable conditions
– Careful setting on audio levels
Slide from Richard Sproat J. Gustafson, CTT, KTH
Labeling DiphonesLabeling DiphonesLabeling DiphonesLabeling Diphones
• Run an ASR in forced alignment mode– Forced alignment:
• In: A trained ASR system, a wavefile, a word transcription of the wavefile
• Returns: an alignment of the phones in the words to the wavefile.
• Much easier than phonetic labeling:– The words are defined
– The phone sequence is generally defined
– They are clearly articulated
– But sometimes speaker still pronounces wrong, so need to check.
• Phone boundaries less important– +- 10 ms is okay
• Midphone boundaries important– Where is the stable part
– Can it be automatically found?
Slide from Richard Sproat
Talsyntes: Joakim Gustafson
Tal, musik och hörsel
8
J. Gustafson, CTT, KTH
Finding diphone boundariesFinding diphone boundariesFinding diphone boundariesFinding diphone boundaries
• Stable part in phonesFor stops: one third in
For phone-silence: one quarter in
For other diphones: 50% in
• In time alignment case:Given explicit known diphone boundaries in prompt in the label file
Use dynamic time warping to find same stable point in new speech
• Optimal couplingTaylor and Isard 1991, Conkie and Isard 1996
Instead of precutting the diphones� Wait until we are about to concatenate the diphones together
� Then take the 2 complete (uncut diphones)
� Find optimal join points by measuring cepstral distance at potential join points, pick best
Slide from Richard Sproat J. Gustafson, CTT, KTH
Summary: Diphone SynthesisSummary: Diphone SynthesisSummary: Diphone SynthesisSummary: Diphone Synthesis
• Well-understood, mature technology
• Augmentations– Stress
– Onset/coda
– Demi-syllables
• Problems:– Signal processing still necessary for modifying durations
– Source data is still not natural
– Units are just not large enough; can’t handle word-specific effects, etc
Slide from Dan Jurafsky
J. Gustafson, CTT, KTH
From diphone synthesis to From diphone synthesis to From diphone synthesis to From diphone synthesis to
Unit Selection SynthesisUnit Selection SynthesisUnit Selection SynthesisUnit Selection Synthesis
• Natural data solves problems with diphones– Diphone databases are carefully designed but:
• Speaker makes errors• Speaker doesn’t speak intended dialect• Require database design to be right
– If it’s automatic• Labeled with what the speaker actually said• Coarticulation, schwas, flaps are natural
• “There’s no data like more data”– Lots of copies of each unit copies of each unit copies of each unit copies of each unit mean you can choose just the
right one for the context– Larger units Larger units Larger units Larger units mean you can capture wider effects
Slide from Dan Jurafsky J. Gustafson, CTT, KTH
UnitUnitUnitUnit selectionselectionselectionselection SynthesisSynthesisSynthesisSynthesis
Slide from Tokuda
J. Gustafson, CTT, KTH
Unit Selection IntuitionUnit Selection IntuitionUnit Selection IntuitionUnit Selection Intuition
• Given a big database
• For each segment that we want to synthesize– Find the unit in the database that is the best to synthesize this target
segment
• What does “best” mean?– Target cost: Target cost: Target cost: Target cost: Closest match to the target description, in terms of
• Phonetic context
• Pitch, power, duration, phrase position
– Concatenation cost: Concatenation cost: Concatenation cost: Concatenation cost: The difference between the end of diphone 1 and the start of diphone 2:
• Matching formants + other spectral characteristics
• Matching energy
• Matching F0
Slide from Dan Jurafsky
Assignment 1: Practical exercises with the calculation of target and concatenation cost.
J. Gustafson, CTT, KTH 48
Target Target Target Target costcostcostcost measuresmeasuresmeasuresmeasures
∑ −=
i
iiyxD ||
Euclidean distanceManhattan (City block) distance
∑ −=
i
ii yxD2)(
Talsyntes: Joakim Gustafson
Tal, musik och hörsel
9
J. Gustafson, CTT, KTH 49
ConcatenationConcatenationConcatenationConcatenation costcostcostcost measuresmeasuresmeasuresmeasures
• Kullback-Leibler distance
• Mahalanobis distance ∑−
=2
2)(
i
iiyx
Dσ
i
iN
i iiy
xyxD log)(
1∑=
−=
Mahalanobis distance Mahalanobis distance Mahalanobis distance Mahalanobis distance is useful in when multi-normal distributions lead to non spherically symmetric distributions
J. Gustafson, CTT, KTH 50
The units in Unit SelectionThe units in Unit SelectionThe units in Unit SelectionThe units in Unit Selection
• Different types Different types Different types Different types of units: e.g. diphones, phones, syllables, words, etc.
• Multiple occurrences Multiple occurrences Multiple occurrences Multiple occurrences of the units cover a wide space of the spectral and prosodic parameters
• Units nearest in this space to the targets will be chosen and will require only minor modificationminor modificationminor modificationminor modification
• The corpus is segmented into phonetic units, indexed, and used asindexed, and used asindexed, and used asindexed, and used as----isisisis
• Selection is made onononon----linelinelineline
• The trend is towards longer and longer unitslonger unitslonger unitslonger units
1999 2000 2001 2002 2003 2004 2005
Sound (OLE2) Sound (OLE2)Sound (OLE2) (.wav)
(.wav) (.wav)
J. Gustafson, CTT, KTH 51
• Large databases of recorded natural speech
• Minimal processing
• Annotation of database – what information is needed?
• Few cuts > maximally long units selected(but context and prosody must fit well)
• Target and concatenation costs
Slide from Dan Jurafsky
Features of Unit Selection SynthesisFeatures of Unit Selection SynthesisFeatures of Unit Selection SynthesisFeatures of Unit Selection Synthesis
J. Gustafson, CTT, KTH
Database creation: Database creation: Database creation: Database creation:
a good speakera good speakera good speakera good speaker• Professional speakers are always better:
– Consistent style and articulation
– Although these databases are carefully labeled
• Ideally (according to AT&T experiments):– Record 20 professional speakers (small amounts of data)
– Build simple synthesis examples
– Get many (200?) people to listen and score them
– Take best voices
• Correlates for human preferences:– High power in unvoiced speech
– High power in higher frequencies
– Larger pitch range
Text from Paul Taylor and Richard Sproat
J. Gustafson, CTT, KTH
Database creation: Database creation: Database creation: Database creation:
good recording conditionsgood recording conditionsgood recording conditionsgood recording conditions
• Good script– Application dependent helps
• Good word coverage• News data synthesizes as news data• News data is bad for dialog.
– Good phonetic coverage, especially wrt context– Low ambiguity– Easy to read
• Annotate at phone level, with stress, word information, phrase breaks
Text from Paul Taylor and Richard Sproat J. Gustafson, CTT, KTH
Creating databaseCreating databaseCreating databaseCreating database
• Unlike diphone synthesis, prosodic variation is a good thing
• Accurate annotation is crucial
• Pitch annotation needs to be very accurate
• Phone alignments can be done automatically, as described for
diphones
Slide from Dan Jurafsky
Talsyntes: Joakim Gustafson
Tal, musik och hörsel
10
J. Gustafson, CTT, KTH
Practical System IssuesPractical System IssuesPractical System IssuesPractical System Issues
• Size of typical system (Rhetorical rVoice):– ~300M
• Speed:– For each diphone, average of 1000 units to choose from, so:
– 1000 target costs
– 1000x1000 join costs
– Each join cost, say 30x30 float point calculations
– 10-15 diphones per second
– 10 billion floating point calculations per second
• But commercial systems must run ~50x faster than real time
• Heavy pruning essential: – 1000 units -> 25 units
Slide from Paul Taylor J. Gustafson, CTT, KTH
Summary: Unit SelectionSummary: Unit SelectionSummary: Unit SelectionSummary: Unit Selection
• Advantages– Quality is far superior to diphones
– Natural prosody selection sounds better
– Non-linguistic features of the speakers voice built in
• Disadvantages:– Fixed voice
– Quality can be very bad in places
• HCI problem: mix of very good and very bad is quite annoying
– Large footprint, itis computationally expensive
– Can’t synthesize everything you want:• Diphone technique can move emphasis
• Unit selection gives good (but possibly incorrect) result
Slide from Richard Sproat
J. Gustafson, CTT, KTH
From Unit selection From Unit selection From Unit selection From Unit selection
to HMM synthesisto HMM synthesisto HMM synthesisto HMM synthesis• Problems with Unit Selection Synthesis
– Discontinuities:Discontinuities:Discontinuities:Discontinuities: Can’t modify signal
– Hit or miss: Hit or miss: Hit or miss: Hit or miss: database often doesn’t have exactly what you want
– Fixed voice Fixed voice Fixed voice Fixed voice
• Solution: HMM (Hidden Markov Model) Synthesis– Stable, Smooth and easy to create multiple voicesStable, Smooth and easy to create multiple voicesStable, Smooth and easy to create multiple voicesStable, Smooth and easy to create multiple voices
– Sounds unnatural to researchers, but naïve subjects prefer itnaïve subjects prefer itnaïve subjects prefer itnaïve subjects prefer it
Example: Nina as unit selection and HMM synthesis voice
Slide from Dan Jurafsky J. Gustafson, CTT, KTH
HMM HMM HMM HMM SynthesisSynthesisSynthesisSynthesis
Slide from Tokuda
J. Gustafson, CTT, KTH 59
HiddenHiddenHiddenHidden MarkovMarkovMarkovMarkov ModelsModelsModelsModels
• A HMM is a machine, with a limited number of possible states.
• The transition between two states is regulated by probabilities.
• Every transition results in an observation with a certain probability.
• The states are hidden, only the observations are visible.
PiiPij
Pjj
Pjk
Pjk
Pkl
Pll
Oi OjOk Ol
J. Gustafson, CTT, KTH 60
HMMsHMMsHMMsHMMs in in in in synthesissynthesissynthesissynthesis
Talsyntes: Joakim Gustafson
Tal, musik och hörsel
11
J. Gustafson, CTT, KTH 61
RelationshipRelationshipRelationshipRelationship betweenbetweenbetweenbetween unitunitunitunitselectionselectionselectionselection and HMM and HMM and HMM and HMM synthesissynthesissynthesissynthesis
Slide from Tokuda J. Gustafson, CTT, KTH 62
RelationshipRelationshipRelationshipRelationship betweenbetweenbetweenbetween unitunitunitunitselectionselectionselectionselection and HMM and HMM and HMM and HMM synthesissynthesissynthesissynthesis 2222
Slide from Tokuda
J. Gustafson, CTT, KTH 63
TheTheTheThe trainingtrainingtrainingtraining partpartpartpart• The training is automatic. You need:
– The text + recordings of about 1000 sentences
• The training of 1000 sentences– takes 24 hours and generates a voice of less than 1 MB
• Separate HMMs for: Spectrum, F0, Duration
• Training in two steps:1. Context independent models2. Use these models to create context dependent models.
• Clustering:– Storing all contexts requires much space– It may be difficult to find alternatives for missing models– Many models are very similar = redundancy
J. Gustafson, CTT, KTH 64
ExamplesExamplesExamplesExamples of features in HMM of features in HMM of features in HMM of features in HMM synthesissynthesissynthesissynthesis trainingtrainingtrainingtraining
• Segment features: – immediate context– position in syllable
• Syllable features – Stress and lexical accent type– position in word and phrase
• Word features – number of syllables– position in phrase– morphological feature (compound or not)– part-of-speech tag (content or function word)
• Phrase features– phrase length in terms of syllables and words
• Utterance features:– length in syllables, words and phrases
• Speaker– Dialect, speaking style, emotional state
J. Gustafson, CTT, KTH 65
ClusteringClusteringClusteringClustering• Groups a large database into clusters
• Three trees: Duration, F0 and Spectrum
• Division based on yes/no questions– Grouping acoustic similar phonemes
– Features.
– Context.
J. Gustafson, CTT, KTH 66
Speaker adaptationSpeaker adaptationSpeaker adaptationSpeaker adaptation
http://homepages.inf.ed.ac.uk/jyamagis/Demo-
html/map-new.html
Talsyntes: Joakim Gustafson
Tal, musik och hörsel
12
J. Gustafson, CTT, KTH
Dalarna Norrland Skåne Gotland SvealandGötaland
vart tar universum slut?
centerpartister och kristdemokrater menar dock att brudparet
kan slippa betala det kan bådas föräldrar göra
gula sidorna finns från och med i fredags sökbart via
mobiltelefonen
om man till exempel tar en telefon och frågar hur den fungerar så
svarar vetenskapsmannen med att lyfta på luren och slå numret
Exempel från Exempel från Exempel från Exempel från SimulektSimulektSimulektSimulekt----projektetprojektetprojektetprojektet
J. Gustafson, CTT, KTH 68
UseUseUseUse of HMM of HMM of HMM of HMM synthesissynthesissynthesissynthesis
• Various voices:– Speaker adaptation
– Speaker interpolation
• Security of speaker identification systems
• Very low bit rate speech coder
• Small footprint, for use in mobile phones and web browsers
– E.g. in flash: http://www.furui.cs.titech.ac.jp/~dixonp/hts/index.html