1 / 18

Text to Speech for In-car Navigation Systems

Text to Speech for In-car Navigation Systems. Luisa Cordano August 8, 2006. TTS in the Navigation Domain. Flexibility Perfect pronunciation Cost savings Expressivity. What kind of expectations does the Navigation market have on a TTS system when applying it in its domain?.

Download Presentation

Text to Speech for In-car Navigation Systems

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Text to Speech for In-car Navigation Systems Luisa Cordano August 8, 2006

  2. TTS in the Navigation Domain • Flexibility • Perfect pronunciation • Cost savings • Expressivity What kind of expectations does the Navigation market have on a TTS system when applying it in its domain?

  3. Key aspects of a TTS system • Unit Selection Technique • Domain-dependent customization • Phonetic Input Interface • Native vs. Foreign Pronunciation

  4. The importance of Unit Selection TTS • Loquendo TTS is a general purpose (Unrestricted) Text-to-Speech system based on the Unit Selection Speech Synthesis Technique • The Unit Selection Technique is at present the only existing technique that enables natural sounding speech • Its basic idea is to concatenate long phoneme sequences extracted from large DataBases of speech recorded by a single voice talent • Advantages: little speech processing, the natural voice timbre is preserved • Drawbacks: scarce control, speech quality depends on the contents of the database

  5. Unit Selection TTS Language Libraries Domain-representative large text corpus Input text ITALIAN Statistical Tools for Database Design SPANISH TEXT ANALYZER ENGLISH Dense text corpus ... phonemes&prosodic labels (&prosodic values) Tools for: Speech Acquisition Phoneme Segmentation Signal Analysis SPEECH SYNTHESIZER ITALIAN female voice SPAGNOLO Vocal DataBases ... ITALIAN Voice-2 SPAGNOLO SPANISH male voice speech ... ... ...

  6. The Synthesis Algorithm Vocal DataBase • define a synthesis TARGET p r `o v a d i s `i n t e s i P P P P P P P P C C C C C W ... p r `o s a e l e g `a n t e... P P PP P P P P P P PP PPP P P P P PPPPPP • match phonetic and prosodic labels • look for similar f0 values at unit junctions • preferably cut units at diphone boundaries • concatenate waveforms • adjust f0 to remove jumps (pitch scaling) ..r i n: `o v a d i s `o l i t o ... P PP P P P P P P P P P P P P PPP S S S S SS SS UU p r `o v a d i s `i n t e s i ...l a f o t o s `i n t e s i PPP P PPPP PP PPPP C CCCCCCCCCWW

  7. Domain Dependent Customization • Loquendo TTS can read any text • In order to improve accuracy and fluency on an application domain it can be customized • Lexical customization: adapting Text-to-Phoneme conversion via Pronunciation Lexicon, Phonetic Input • Vocal customization: enhancing the Vocal DataBase with application prompts and recurrent phrases

  8. Domain Dependent Customization • Thenavigation domain: • A limited number of recurring phrases: Ex. “turn left”, “…” • A peculiar and huge lexical domain: addresses, names and toponyms: due to their they historical/foreign origin, they do not necessarily follow the standard grapheme-to-phoneme rules of the language • Customizing Loquendo TTSfor Navigation: • Navigation Vocal Add-On: the recurring phrases can be recorded in case their synthesis does not sound perfect • The exact pronunciation of names and addresses can be specified via the Phonetic Input Interface or via the Pronunciation Lexicon (this does not prevent from possible acoustic defects)

  9. Phonetic Input Interface • Loquendo TTS let the User control the exact pronunciation of words • An escape sequence in the input text allows skipping the grapheme-to-phoneme process driven by the Language Library… • And inputting the desired phoneme sequence directly to the Speech Synthesis process based on the Vocal Database

  10. Phonetic Input Interface Language Libraries Input text ITALIAN SPANISH Input Phonetic Transcription (language independent SAMPA Alphabet) TEXT ANALYZER ENGLISH ... phonemes&prosodic labels (&prosodic values) SPEECH SYNTHESIZER ITALIAN female voice SPAGNOLO Vocal DataBases ... ITALIAN Voice-2 SPAGNOLO SPANISH male voice speech ...

  11. Phonetic Input Interface • The special feature is the language independence • The input phonemes are Mapped on the Phonemes of the Voice Via the Phonetic Interface, an Italian voice can be made to pronounce \SAMPA="san$te$na for the Italian name “Santena”, overriding the the default san“tena. But also \SAMPA=% le#"gRa~Z For the French “Les Granges”, otherwise transcribed les#"grandges. The foreign R and a~ will be mapped on the Italian r and a

  12. Native vs Foreign Pronunciation • Each Voice has its own native language • Each Vocal DataBase has its own: • Phoneme Set (the db does not contain foreign phonemes) • Coverage of Phoneme Sequences (the db contains only sequences that frequent in its native language) • The Foreign Pronunciation feature of Loquendo TTS maps foreign phonemes onto the most similar native phonemes. • But it can’t avoid obtaining phoneme sequences not present in the Vocal DB, requiring the concatenation of shorter speech units. • Foreign Pronunciation is: • Plausible • Approximated • Sometimes choppy

  13. Foreign Pronunciation: the Phoneme Mapping Algorithm The algorithm centers around a Phonetic Similarity Function (PSF) that computes a similarity score of two phonemes that only depends on their phonetic-articulatory features Such an approach overlooks: • Finer language specific aspects of speech perception • Pragmatic/cultural aspects that may affect foreign pronunciation But… makes comparison between phonemes free from any language-specific knowledge!

  14. Phonetic Similarity Function This approach requires, as a first step, the definition of a vector of phonetic-articulatory features for each phoneme Each feature has a different weight in the computation of phonetic similarity Values of a non-binary feature are placed in a scale of perceptual distance Tongue Position Tonicity Non-binary features Binary feature

  15. Foreign Pronunciation: Demos English Text: “Good afternoon everybody! This is a live demo of Loquendo's lifelike text-to-speech technology, using the mixed language feature” Katrin (German Voice) Jorge (Spanish Voice) Bernard (French Voice) Interactive demos are available on http://actor.loquendo.com/actordemo/

  16. Foreign Pronunciation: Navigation Demos Dave (American Voice) Kate (British Voice) “In 250 yards, bear left, at the roundabout, take the second exit, and follow the signpost indicating, Charles de Gaulle airport.” “In 100 yards, stay in the right lane, and take the main road. After the tunnel, turn left, and follow the signpost indicating, Fiumicino, Leonardo da Vinci airport.”

  17. Future Works for the Foreign Pronunciation The problem of the the unusual sequences of phones could be partially solved by : • Augmenting the speech databases with ad-hoc vocal material • Rewriting the PMM output by reducing the number of unusual phoneme sequences without modifying the plausibility of the reading • Adding new spectral features to better describe each speech database phone

More Related