paper-with-me

Papers

Speechless: Speech Instruction Training Without Speech for Low Resource Languages

2025-05-23 · Alan Dao, Dinh Bach Vu, Huy Hoang Ha, Tuan Le Duc Anh, Shreyas Gopal, Yue Heng Yeo, Warren Keng Hoong Low, Eng Siong Chng, Jia Qi Yip

The rapid growth of voice assistants powered by large language models (LLM) has highlighted a need for speech instruction data to train these systems. Despite the abundance of speech recognition data, there is a notable scarcity of speech instruction data, which is essential for fine-tuning models to understand and execute spoken commands. Generating high-quality synthetic speech requires a good text-to-speech (TTS) model, which may not be available to low resource languages. Our novel approach addresses this challenge by halting synthesis at the semantic representation level, bypassing the need for TTS. We achieve this by aligning synthetic semantic representations with the pre-trained Whisper encoder, enabling an LLM to be fine-tuned on text instructions while maintaining the ability to understand spoken instructions during inference. This simplified training process is a promising approach to building voice assistant for low-resource languages.

📄 PDF Abstract BibTeX arXiv:2505.17417

Code (1)

menloresearch/ichigo 공식 구현 pytorch

Tasks

speech-recognitionSpeech Recognitiontext-to-speechText to Speech

Similar Papers 제목 키워드 기반

SpeechLess: Micro-utterance with Personalized Spatial Memory-aware Assistant in Everyday Augmented Reality

2026-01-31 · Yoonsang Kim, Devshree Jadeja, Divyansh Pradhan, Yalong Yang 외 arxiv

Speaking aloud to a wearable AR assistant in public can be socially awkward, and re-articulating the same requests every day creates unnecessary effort. We present SpeechLess, a wearable AR assistant that introduces a sp…

Vision-Speech Models: Teaching Speech Models to Converse about Images

2025-03-19 · Amélie Royer, Moritz Böhle, Gabriel de Marmiesse, Laurent Mazaré 외

The recent successes of Vision-Language models raise the question of how to equivalently imbue a pretrained speech model with vision understanding, an important milestone towards building a multimodal speech model able t…

parameter-efficient fine-tuning

Unlocking Speech-Text Compositional Powers: Instruction-Following Speech Language Models without Instruction Tuning

2026-07-02 · Congrui Du, Yang Zhang, Kaizhi Qian, Shiyu Chang arxiv

Instruction tuning for speech language models (SLMs) is substantially more challenging than for text-based large language models (LLMs), as it requires learning a new modality and a wide range of speech-specific instruct…

Instruction-Following Speech Recognition

2023-09-18 · Cheng-I Jeff Lai, Zhiyun Lu, Liangliang Cao, Ruoming Pang

Conventional end-to-end Automatic Speech Recognition (ASR) models primarily focus on exact transcription tasks, lacking flexibility for nuanced user interactions. With the advent of Large Language Models (LLMs) in speech…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Instruction Followingspeech-recognition+1

SpeechMapper: Speech-to-text Embedding Projector for LLMs

2026-01-28 · Biswesh Mohapatra, Marcely Zanon Boito, Ioan Calapodescu arxiv

Current speech LLMs bridge speech foundation models to LLMs using projection layers, training all of these components on speech instruction data. This strategy is computationally intensive and susceptible to task and pro…

Question Answering