Nothing Special   »   [go: up one dir, main page]

Zhou et al., 1997 - Google Patents

An approach to continuous speech recognition based on layered self-adjusting decoding graph

Zhou et al., 1997

View PDF
Document ID
17588113914850957961
Author
Zhou Q
Chou W
Publication year
Publication venue
1997 IEEE International Conference on Acoustics, Speech, and Signal Processing

External Links

Snippet

In this paper, an approach to continuous speech recognition based on a layered self- adjusting decoding graph is described. It utilizes a scaffolding layer to support fast network expansion and releasing. A two level hashing structure is also described. It introduces self …
Continue reading at www2.spsc.tugraz.at (PDF) (other versions)

Classifications

    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/08—Speech classification or search
    • G10L15/18—Speech classification or search using natural language modelling
    • G10L15/183—Speech classification or search using natural language modelling using context dependencies, e.g. language models
    • G10L15/187—Phonemic context, e.g. pronunciation rules, phonotactical constraints or phoneme n-grams
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06F—ELECTRICAL DIGITAL DATA PROCESSING
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/30—Information retrieval; Database structures therefor; File system structures therefor

Similar Documents

Publication Publication Date Title
Aubert An overview of decoding techniques for large vocabulary continuous speech recognition
EP1133766B1 (en) Network and language models for use in a speech recognition system
US7127396B2 (en) Method and apparatus for speech synthesis without prosody modification
Ortmanns et al. Language-model look-ahead for large vocabulary speech recognition
US6073095A (en) Fast vocabulary independent method and apparatus for spotting words in speech
Ries HMM and neural network based speech act detection
KR970029146A (en) Pre-search apparatus and method for performing a search with Lattice as a key
EP1738291A1 (en) Tree index based method for accessing automatic directory
US7035802B1 (en) Recognition system using lexical trees
CN108288468A (en) Audio recognition method and device
GB2453366A (en) Automatic speech recognition method and apparatus
Zhou et al. An approach to continuous speech recognition based on layered self-adjusting decoding graph
KR20080069990A (en) Computer-readable media with voice segment indexing and retrieval methods and computer executable instructions
US6006181A (en) Method and apparatus for continuous speech recognition using a layered, self-adjusting decoder network
CN106297766B (en) Phoneme synthesizing method and system
CN112669815B (en) Song customization generation method and corresponding device, equipment and medium thereof
US7328157B1 (en) Domain adaptation for TTS systems
CN110942765B (en) Method, device, server and storage medium for constructing corpus
Tran et al. A word graph based n-best search in continuous speech recognition
CN110516053B (en) Dialogue processing method, device and computer storage medium
US6442520B1 (en) Method and apparatus for continuous speech recognition using a layered, self-adjusting decoded network
CN1312542A (en) Speech refusal using mark with language limitation
US20050015734A1 (en) Method and apparatus for minimizing weighted networks with link and node labels
Eide Automatic modeling of pronunciation variations
Burhke et al. A wave decoder for continuous speech recognition