paper-with-me

Papers

LAST: Language Model Aware Speech Tokenization

2024-09-05 · Arnon Turetzky, Yossi Adi

Speech tokenization serves as the foundation of speech language model (LM), enabling them to perform various tasks such as spoken language modeling, text-to-speech, speech-to-text, etc. Most speech tokenizers are trained independently of the LM training process, relying on separate acoustic models and quantization methods. Following such an approach may create a mismatch between the tokenization process and its usage afterward. In this study, we propose a novel approach to training a speech tokenizer by leveraging objectives from pre-trained textual LMs. We advocate for the integration of this objective into the process of learning discrete speech representations. Our aim is to transform features from a pre-trained speech model into a new feature space that enables better clustering for speech LMs. We empirically investigate the impact of various model design choices, including speech vocabulary size and text LM size. Our results demonstrate the proposed tokenization method outperforms the evaluated baselines considering both spoken language modeling and speech-to-text. More importantly, unlike prior work, the proposed method allows the utilization of a single pre-trained LM for processing both speech and text inputs, setting it apart from conventional tokenization approaches.

📄 PDF Abstract BibTeX arXiv:2409.03701

Code (0)

등록된 구현이 없습니다.

Tasks

Language ModelingLanguage ModellingmodelQuantizationSpeech TokenizationSpeech-to-Texttext-to-speechText to Speech

Similar Papers 제목 키워드 기반

Sylber: Syllabic Embedding Representation of Speech from Raw Audio

2024-10-09 · Cheol Jun Cho, Nicholas Lee, Akshat Gupta, Dhruv Agarwal 외

Syllables are compositional units of spoken language that efficiently structure human speech perception and production. However, current neural speech representations lack such structure, resulting in dense token sequenc…

Language ModelingLanguage ModellingSelf-Supervised LearningSpeech Tokenization

Exploring the Effect of Segmentation and Vocabulary Size on Speech Tokenization for Speech Language Models

2025-05-23 · Shunsuke Kando, Yusuke Miyao, Shinnosuke Takamichi

The purpose of speech tokenization is to transform a speech signal into a sequence of discrete representations, serving as the foundation for speech language models (SLMs). While speech tokenization has many options, the…

Speech TokenizationSpoken Language Understanding

StreamAlign: Streaming Text-Aligned Speech Tokenization

2026-09-09 · Kang-wook Kim, Jinyoung Park, Jinsoo Kim, Sehun Lee 외 arxiv

Text-aligned speech tokenization methods have emerged to better align speech tokens with LLM token spaces, enabling more effective utilization of pretrained LLMs. However, they rely on offline automatic speech recognitio…

Speech Recognition

RepCodec: A Speech Representation Codec for Speech Tokenization

2023-08-31 · Zhichao Huang, Chutong Meng, Tom Ko

With recent rapid growth of large language models (LLMs), discrete speech tokenization has played an important role for injecting speech into LLMs. However, this discretization gives rise to a loss of information, conseq…

Language ModelingLanguage ModellingQuantizationSpeech Tokenization

TASTE: Text-Aligned Speech Tokenization and Embedding for Spoken Language Modeling

2025-04-09 · Liang-Hsuan Tseng, Yi-Chang Chen, Kuan-Yi Lee, Da-Shan Shiu 외

Recent efforts target spoken language models (SLMs) that not only listen but also speak for more natural human-LLM interaction. Joint speech-text modeling is a promising direction to achieve this. However, the effectiven…

Language ModelingLanguage Modellingparameter-efficient fine-tuningSpeech Tokenization