paper-with-me

Papers

Phonetic-assisted Multi-Target Units Modeling for Improving Conformer-Transducer ASR system

2022-11-03 · Li Li, Dongxing Xu, Haoran Wei, Yanhua Long

Exploiting effective target modeling units is very important and has always been a concern in end-to-end automatic speech recognition (ASR). In this work, we propose a phonetic-assisted multi target units (PMU) modeling approach, to enhance the Conformer-Transducer ASR system in a progressive representation learning manner. Specifically, PMU first uses the pronunciation-assisted subword modeling (PASM) and byte pair encoding (BPE) to produce phonetic-induced and text-induced target units separately; Then, three new frameworks are investigated to enhance the acoustic encoder, including a basic PMU, a paraCTC and a pcaCTC, they integrate the PASM and BPE units at different levels for CTC and transducer multi-task training. Experiments on both LibriSpeech and accented ASR tasks show that, the proposed PMU significantly outperforms the conventional BPE, it reduces the WER of LibriSpeech clean, other, and six accented ASR testsets by relative 12.7%, 6.0% and 7.7%, respectively.

📄 PDF Abstract BibTeX arXiv:2211.01571

Code (0)

등록된 구현이 없습니다.

Tasks

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Representation Learningspeech-recognitionSpeech Recognition

Methods 이 논문이 사용한 방법론

BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…

Similar Papers 제목 키워드 기반

Language-universal phonetic encoder for low-resource speech recognition

2023-05-19 · Siyuan Feng, Ming Tu, Rui Xia, Chuanzeng Huang 외

Multilingual training is effective in improving low-resource ASR, which may partially be explained by phonetic representation sharing between languages. In end-to-end (E2E) ASR systems, graphemes are often used as basic …

Decoderspeech-recognitionSpeech Recognition

The Role of Phonetic Units in Speech Emotion Recognition

2021-08-02 · Jiahong Yuan, Xingyu Cai, Renjie Zheng, Liang Huang 외

We propose a method for emotion recognition through emotiondependent speech recognition using Wav2vec 2.0. Our method achieved a significant improvement over most previously reported results on IEMOCAP, a benchmark emoti…

Emotion RecognitionSpeech Emotion Recognitionspeech-recognitionSpeech Recognition

An Information-Theoretic Analysis of Self-supervised Discrete Representations of Speech

2023-06-04 · Badr M. Abdullah, Mohammed Maqsood Shaik, Bernd Möbius, Dietrich Klakow

Self-supervised representation learning for speech often involves a quantization step that transforms the acoustic input into discrete units. However, it remains unclear how to characterize the relationship between these…

QuantizationRepresentation Learning

Context-aware Goodness of Pronunciation for Computer-Assisted Pronunciation Training

2020-08-19

Mispronunciation detection is an essential component of the Computer-Assisted Pronunciation Training (CAPT) systems. State-of-the-art mispronunciation detection models use Deep Neural Networks (DNN) for acoustic modeling…

Sentence

Exploring the Benefits of Tokenization of Discrete Acoustic Units

2024-06-08 · Avihu Dekel, Raul Fernandez

Tokenization algorithms that merge the units of a base vocabulary into larger, variable-rate units have become standard in natural language processing tasks. This idea, however, has been mostly overlooked when the vocabu…

Language ModelingLanguage Modelling