paper-with-me

Papers

TokenSplit: Using Discrete Speech Representations for Direct, Refined, and Transcript-Conditioned Speech Separation and Recognition

2023-08-21 · Hakan Erdogan, Scott Wisdom, Xuankai Chang, Zalán Borsos, Marco Tagliasacchi, Neil Zeghidour, John R. Hershey

We present TokenSplit, a speech separation model that acts on discrete token sequences. The model is trained on multiple tasks simultaneously: separate and transcribe each speech source, and generate speech from text. The model operates on transcripts and audio token sequences and achieves multiple tasks through masking of inputs. The model is a sequence-to-sequence encoder-decoder model that uses the Transformer architecture. We also present a "refinement" version of the model that predicts enhanced audio tokens from the audio tokens of speech separated by a conventional separation model. Using both objective metrics and subjective MUSHRA listening tests, we show that our model achieves excellent performance in terms of separation, both with or without transcript conditioning. We also measure the automatic speech recognition (ASR) performance and provide audio samples of speech synthesis to demonstrate the additional utility of our model.

📄 PDF Abstract BibTeX arXiv:2308.10415

Code (0)

등록된 구현이 없습니다.

Tasks

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Decoderspeech-recognitionSpeech RecognitionSpeech SeparationSpeech Synthesis

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Position-Wise Feed-Forward Layer 설명 없음
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…
Adam 설명 없음
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…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…

Similar Papers 제목 키워드 기반

Language-Codec: Bridging Discrete Codec Representations and Speech Language Models

2024-02-19 · Shengpeng Ji, Minghui Fang, Jialong Zuo, Ziyue Jiang 외

In recent years, large language models have achieved significant success in generative tasks related to speech, audio, music, and other signal domains. A crucial element of these models is the discrete acoustic codecs, w…

Audio CompressionAudio GenerationQuantization

Direct Simultaneous Speech-to-Speech Translation with Variational Monotonic Multihead Attention

2021-10-15 · Xutai Ma, Hongyu Gong, Danni Liu, Ann Lee 외

We present a direct simultaneous speech-to-speech translation (Simul-S2ST) model, Furthermore, the generation of translation is independent from intermediate text representations. Our approach leverages recent progress o…

Simultaneous Speech-to-Speech TranslationSpeech SynthesisSpeech-to-Speech TranslationTranslation

vq-wav2vec: Self-Supervised Learning of Discrete Speech Representations

2019-10-12 · ICLR 2020 1 · Alexei Baevski, Steffen Schneider, Michael Auli

We propose vq-wav2vec to learn discrete representations of audio segments through a wav2vec-style self-supervised context prediction task. The algorithm uses either a gumbel softmax or online k-means clustering to quanti…

ClusteringGeneral ClassificationSelf-Supervised Learningspeech-recognition+1

Improving Direct Persian-English Speech-to-Speech Translation with Discrete Units and Synthetic Parallel Data

2025-11-16 · Sina Rashidi, Hossein Sameti arxiv

Direct speech-to-speech translation (S2ST), in which all components are trained jointly, is an attractive alternative to cascaded systems because it offers a simpler pipeline and lower inference latency. However, direct …

Speech-to-Speech Translation

Direct speech-to-speech translation with discrete units

2021-07-12 · ACL 2022 5 · Ann Lee, Peng-Jen Chen, Changhan Wang, Jiatao Gu 외

We present a direct speech-to-speech translation (S2ST) model that translates speech from one language to speech in another language without relying on intermediate text generation. We tackle the problem by first applyin…

Speech-to-Speech TranslationText GenerationTranslation