paper-with-me

Papers

A Weakly-Supervised Streaming Multilingual Speech Model with Truly Zero-Shot Capability

2022-11-04 · Jian Xue, Peidong Wang, Jinyu Li, Eric Sun

In this paper, we introduce our work of building a Streaming Multilingual Speech Model (SM2), which can transcribe or translate multiple spoken languages into texts of the target language. The backbone of SM2 is Transformer Transducer, which has high streaming capability. Instead of human labeled speech translation (ST) data, SM2 models are trained using weakly supervised data generated by converting the transcriptions in speech recognition corpora with a machine translation service. With 351 thousand hours of anonymized speech training data from 25 languages, SM2 models achieve comparable or even better ST quality than some recent popular large-scale non-streaming speech models. More importantly, we show that SM2 has the truly zero-shot capability when expanding to new target languages, yielding high quality ST results for {source-speech, target-text} pairs that are not seen during training.

📄 PDF Abstract BibTeX arXiv:2211.02499

Code (0)

등록된 구현이 없습니다.

Tasks

Machine Translationspeech-recognitionSpeech RecognitionTranslation

Methods 이 논문이 사용한 방법론

Golden Queue Managers 설명 없음
Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Adam 설명 없음
Position-Wise Feed-Forward Layer 설명 없음

Similar Papers 제목 키워드 기반

Weakly Supervised POS Taggers Perform Poorly on Truly Low-Resource Languages

2020-04-28 · Katharina Kann, Ophélie Lacroix, Anders Søgaard

Part-of-speech (POS) taggers for low-resource languages which are exclusively based on various forms of weak supervision - e.g., cross-lingual transfer, type-level supervision, or a combination thereof - have been report…

Cross-Lingual TransferPOSPOS Tagging

Mixture-of-Expert Conformer for Streaming Multilingual ASR

2023-05-25 · Ke Hu, Bo Li, Tara N. Sainath, Yu Zhang 외

End-to-end models with large capacity have significantly improved multilingual automatic speech recognition, but their computation cost poses challenges for on-device applications. We propose a streaming truly multilingu…

Automatic Speech Recognitionspeech-recognitionSpeech Recognition

Low-Resourced Speech Recognition for Iu Mien Language via Weakly-Supervised Phoneme-based Multilingual Pre-training

2024-07-18 · Lukuan Dong, Donghong Qin, Fengbo Bai, Fanhua Song 외

The mainstream automatic speech recognition (ASR) technology usually requires hundreds to thousands of hours of annotated speech data. Three approaches to low-resourced ASR are phoneme or subword based supervised pre-tra…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognitionSpeech Recognition

CosyVoice 2: Scalable Streaming Speech Synthesis with Large Language Models

2024-12-13 · Zhihao Du, Yuxuan Wang, Qian Chen, Xian Shi 외

In our previous work, we introduced CosyVoice, a multilingual speech synthesis model based on supervised discrete speech tokens. By employing progressive semantic decoding with two popular generative models, language mod…

In-Context LearningQuantizationSpeech Synthesis

Deploying self-supervised learning in the wild for hybrid automatic speech recognition

2022-05-17 · Mostafa Karimi, Changliang Liu, Kenichi Kumatani, Yao Qian 외

Self-supervised learning (SSL) methods have proven to be very successful in automatic speech recognition (ASR). These great improvements have been reported mostly based on highly curated datasets such as LibriSpeech for …

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Event DetectionScheduling+3