[go: up one dir, main page]

Naowarat et al., 2021 - Google Patents

Reducing spelling inconsistencies in code-switching ASR using contextualized CTC loss

Naowarat et al., 2021

View PDF
Document ID
11805120089993669480
Author
Naowarat B
Kongthaworn T
Karunratanakul K
Wu S
Chuangsuwanich E
Publication year
Publication venue
ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

External Links

Snippet

Code-Switching (CS) remains a challenge for Automatic Speech Recognition (ASR), especially character-based models. With the combined choice of characters from multiple languages, the out-come from character-based models suffers from phoneme duplication …
Continue reading at arxiv.org (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
    • G10L15/19—Grammatical context, e.g. disambiguation of the recognition hypotheses based on word sequence rules
    • G10L15/197—Probabilistic grammars, e.g. word 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
    • G06F17/20—Handling natural language data
    • G06F17/28—Processing or translating of natural language
    • G06F17/2809—Data driven translation
    • G06F17/2827—Example based machine translation; Alignment
    • 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
    • G06F17/20—Handling natural language data
    • G06F17/28—Processing or translating of natural language
    • G06F17/2872—Rule based translation
    • 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
    • G06F17/20—Handling natural language data
    • G06F17/27—Automatic analysis, e.g. parsing
    • G06F17/2705—Parsing
    • 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
    • G06F17/20—Handling natural language data
    • G06F17/27—Automatic analysis, e.g. parsing
    • G06F17/2765—Recognition
    • 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
    • G06F17/20—Handling natural language data
    • G06F17/28—Processing or translating of natural language
    • G06F17/289—Use of machine translation, e.g. multi-lingual retrieval, server side translation for client devices, real-time translation
    • 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
    • G10L15/06—Creation of reference templates; Training of speech recognition systems, e.g. adaptation to the characteristics of the speaker's voice
    • G10L15/065—Adaptation
    • G10L15/07—Adaptation to the speaker
    • 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
    • G10L15/1822—Parsing for meaning understanding
    • 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
    • G06F17/3061—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F17/30634—Querying
    • G06F17/30657—Query processing
    • G06F17/3066—Query translation
    • G06F17/30669—Translation of the query language, e.g. Chinese to English
    • 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
    • G10L15/14—Speech classification or search using statistical models, e.g. hidden Markov models [HMMs]
    • G10L15/142—Hidden Markov Models [HMMs]
    • G10L15/144—Training of HMMs
    • 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
    • G10L15/28—Constructional details of speech recognition systems
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06N—COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N99/00—Subject matter not provided for in other groups of this subclass
    • G06N99/005—Learning machines, i.e. computer in which a programme is changed according to experience gained by the machine itself during a complete run
    • 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
    • G10L15/005—Language recognition
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
    • G10L13/00—Speech synthesis; Text to speech systems
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
    • G10L19/00—Speech or audio signal analysis-synthesis techniques for redundancy reduction, e.g. in vocoders; Coding or decoding of speech or audio signal, using source filter models or psychoacoustic analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06F—ELECTRICAL DIGITAL DATA PROCESSING
    • G06F15/00—Digital computers in general; Data processing equipment in general
    • G06F15/18—Digital computers in general; Data processing equipment in general in which a programme is changed according to experience gained by the computer itself during a complete run; Learning machines

Similar Documents

Publication Publication Date Title
Kürzinger et al. Ctc-segmentation of large corpora for german end-to-end speech recognition
Le et al. Deep shallow fusion for RNN-T personalization
Liao et al. Improving readability for automatic speech recognition transcription
KR102375115B1 (en) Phoneme-Based Contextualization for Cross-Language Speech Recognition in End-to-End Models
Zeyer et al. Improved training of end-to-end attention models for speech recognition
Mairesse et al. Stochastic language generation in dialogue using factored language models
Seki et al. An end-to-end language-tracking speech recognizer for mixed-language speech
US10255275B2 (en) Method and system for generation of candidate translations
JP7678227B2 (en) Joint Unsupervised and Supervised Training (JUST) for Multilingual Automatic Speech Recognition
Park et al. Neural spelling correction: translating incorrect sentences to correct sentences for multimedia
Alrumiah et al. Intelligent Quran Recitation Recognition and Verification: Research Trends and Open Issues
KR20230156795A (en) Word segmentation regularization
Naowarat et al. Reducing spelling inconsistencies in code-switching ASR using contextualized CTC loss
Mandal et al. Futurity of translation algorithms for neural machine translation (NMT) and its vision
Li et al. BAS-ALSTM: analyzing the efficiency of artificial intelligence-based English translation system
Bataev et al. Exploring end-to-end techniques for low-resource speech recognition
Dumyn et al. Review of automatic speech recognition systems for Ukrainian and english language
Baas et al. Transfusion: Transcribing speech with multinomial diffusion
Shunmuga Priya et al. Robust multi-dialect end-to-end asr model jointly with beam search threshold pruning and LLM
Kim et al. Accurate semi-supervised automatic speech recognition via multi-hypotheses-based curriculum learning
Peng et al. An interactive two-pass decoding network for joint intent detection and slot filling
Hyun Park et al. Accurate semi-supervised automatic speech recognition for ordinary and characterized speeches via multi-hypotheses-based curriculum learning
US20250209278A1 (en) Identifying speaker names in transcripts utilizing language models
Ambadekar et al. A review on multilingual voice-to-voice translation
Luo et al. Comparison of Well and Lower-Resourced Self-training in ASR