Voxtlm: Unified Decoder-only Models For Consolidating Speech Recognition/synthesis And Speech/text Continuation Tasks

Abstract

We propose a decoder-only language model, VoxtLM, that can perform four tasks: speech recognition, speech synthesis, text generation, and speech continuation. VoxtLM integrates text vocabulary with discrete speech tokens from self-supervised speech features and uses special tokens to enable multitask learning. Compared to a single-task model, VoxtLM exhibits a significant improvement in speech synthesis, with improvements in both speech intelligibility from 28.9 to 5.6 and objective quality from 2.68 to 3.90. VoxtLM also improves speech generation and speech recognition performance over the single-task counterpart. Further, VoxtLM is trained with publicly available data and training recipes and model checkpoints are open-sourced to make fully reproducible work.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keymaiti2023voxtlm

Related papers

• Investigating Decoder-only Large Language Models For Speech-to-text Translation (2024)0.00
• Viola: Unified Codec Language Models For Speech Recognition, Synthesis, And Translation (2023)0.00
• Syneslm: A Unified Approach For Audio-visual Speech Recognition And Translation Via Language Model And Synthetic Data (2024)0.00
• Discrete Multimodal Transformers With A Pretrained Large Language Model For Mixed-supervision Speech Processing (2024)0.00
• Audiolm: A Language Modeling Approach To Audio Generation (2022)18.91
• Speechverse: A Large-scale Generalizable Audio Language Model (2024)0.00
• Towards Efficient Speech-text Jointly Decoding Within One Speech Language Model (2025)0.00
• LM-VC: Zero-shot Voice Conversion Via Speech Generation Based On Language Models (2023)0.00