arXiv Computation and Language

GSLM2: Multi-Stream Speech Representation Learning and Generative Spoken Language Modeling

GSLM2 is a multi‑stream generative spoken language model that learns complementary speech representations at multiple abstraction levels using the SpidR 2.0 encoder and a shared‑backbone SLM with stream‑specific predictors. It improves linguistic competence and scales more efficiently than prior speech models, narrowing the performance gap with text‑based language models by about two orders of magnitude on several benchmarks. The authors release the training code and checkpoints publicly.

arXiv AI

Oct 26

Uni-Stream: A Unified Streaming Speech Language Model for Speech Synthesis and Recognition

Uni-Stream is a unified streaming speech language model that supports both speech recognition and synthesis within a single architecture. Built on compact pretrained speech models, it processes interleaved text and speech in real time and achieves performance comparable to task‑specific models through a two‑stage training approach. The authors also introduce a data annotation pipeline for streaming training and plan to release the generated transcriptions and word‑level timestamps, while analyzing how speech and text representations occupy distinct latent spaces in the model.

By Xuan Shi, Chang Zeng, Tiantian Feng, Ye Zhang, Jun Liu, Shih-Heng Wang, Lie Lu, Shrikanth Narayanan

llms multimodal

arXiv AI

Aug 25

Do Spoken Language Models Hear Speech as They Read Text? Bridging Structural Gaps Between Speech and Text

The paper investigates how Spoken Language Models (SLMs) process speech compared to text, noting that current SLMs show weak alignment between speech and text representations despite strong downstream performance. The authors propose a framework that separates length mismatch from semantic alignment to better match speech and text representations. Experiments on multiple benchmarks demonstrate that this approach yields competitive results against strong baselines, highlighting the need to explicitly address structural differences between speech and text in SLM training.

By Hyeonyu Kim, Hwayeon Kim, Youngwon Choi, Myeongkyun Cho, Huu-Kim Nguyen

llms benchmarks safety

arXiv AI

Aug 6

Breaking the Curse ofMultilinguality inMany-to-Many Speech-to-Text Translation via a Resource-AwareMixture of Speech Encoders

arXiv:2608. 04586v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) have achieved significant success in speech-to-text translation (S2TT).

By Yexing Du, Kaiyuan Liu, Youcheng Pan, Bo Yang, Chengpeng Fu, Yu Wang, Ming Liu

llms multimodal benchmarks safety

arXiv AI

Jun 10

Speech Meets ELF: Audio Conditional Continuous-Target Diffusion for Speech Recognition and Translation

arXiv:2606. 10368v1 Announce Type: cross Abstract: Speech-to-text (S2T) systems for recognition (ASR) and translation (S2TT) typically generate discrete text tokens.

By Xuanchen Li, Tianrui Wang, Yuheng Lu, Zikang Huang, Yu Jiang, Chenghan Lin, Chenrui Cui, Ziyang Ma, Xingyu Ma, Chunyu Qiang, Guochen Yu, Xie Chen, Longbiao Wang, Jianwu Dang

diffusion multimodal

arXiv AI

Aug 7

Breaking the Curse of Multilinguality in Many-to-Many Speech-to-Text Translation via a Resource-Aware Mixture of Speech Encoders

arXiv:2608. 04586v2 Announce Type: replace-cross Abstract: Multimodal large language models (MLLMs) have achieved significant success in speech-to-text translation (S2TT).

By Yexing Du, Kaiyuan Liu, Youcheng Pan, Bo Yang, Chengpeng Fu, Yu Wang, Ming Liu

llms multimodal benchmarks safety

arXiv AI

Jun 9

End-to-End Training for Discrete Token LLM based TTS System

arXiv:2606. 09234v1 Announce Type: cross Abstract: Recent state-of-the-art (SOTA) text-to-speech (TTS) systems typically adopt a cascaded pipeline consisting of a speech tokenizer, an autoregressive large language model (LLM), and a diffusion based flow-matching (FM) model, with these components trained independently.

By Changfeng Gao, Yong Ren, Jun Yuan, Ye Bai, Zhao You, ShiDong Shang

llms diffusion nlp reinforcement-learning multimodal benchmarks

arXiv Machine Learning

Sep 7

GEPARD - Generative, Prosody-aware, Autoregressive text-to-speech model for Realtime Dialogue

GEPARD is a streaming text‑to‑speech model that uses a standard large language model backbone to generate speech autoregressively, decoding audio with an FSQ‑based neural codec. It streams audio chunk‑by‑chunk as text arrives, achieving a real‑time factor of about 0.067 and an aggregate speedup of roughly 204× on a single GPU with 256 concurrent streams. The design keeps all complex auxiliary mechanisms outside the decode loop, enabling deployment with a standard LLM engine (vLLM) without kernel modifications.

By Denis Pavlov, Ulanbek Abdurazakov, Nursultan Bakashov

llms rag reinforcement-learning efficiency multimodal

arXiv AI

Jun 3

Efficient ASR Training with Conversations that Never Happened

arXiv:2606. 03957v1 Announce Type: cross Abstract: Conversational ASR for lower-resource languages and niche domains is limited by the scarcity of domain-matched multi-speaker training data.

By M\'at\'e Gedeon, P\'eter Mihajlik

llms multimodal benchmarks

Hugging Face Trending Papers

Jun 2

Efficient ASR Training with Conversations that Never Happened

Conversational ASR for lower-resource languages and niche domains is limited by the scarcity of domain-matched multi-speaker training data. We propose an augmentation pipeline that generates scenario-level dialogues with participant metadata, maps speaker attributes to TTS voice profiles, and assembles synthesized utterances into speaker-aware simulated conversations.

llms multimodal benchmarks

arXiv Computation and Language

Sep 22

Efficient and Adaptive Simultaneous Speech Translation with Fully Unidirectional Architecture

arXiv:2504.11809v2 Announce Type: replace Abstract: Simultaneous speech translation (SimulST) produces translations incrementally while processing partial speech input. Although large language models...

By Biao Fu, Donglei Yu, Minpeng Liao, Chengxi Li, Xinjie Chen, Yidong Chen, Kai Fan, Xiaodong Shi

llms

arXiv AI

Jun 16

WavSLM: Single-Stream Speech Language Modeling via WavLM Distillation

arXiv:2603. 05299v2 Announce Type: replace-cross Abstract: Large language models show that simple autoregressive training can yield scalable and coherent generation, but extending this paradigm to speech remains challenging due to the entanglement of semantic and acoustic information.

By Luca Della Libera, Cem Subakan, Mirco Ravanelli

llms efficiency benchmarks

arXiv Computation and Language

Sep 15

Typhoon ASR Streaming: Steerable Low-Latency Thai Speech Recognition with Real-Time Shallow Fusion

arXiv:2609.14991v1 Announce Type: new Abstract: Open Thai automatic speech recognition (ASR) is dominated by offline, Whisper-based models that read the whole utterance before transcribing, ruling ou...

By Warit Sirichotedumrong, Tanawin Samutsin, Shah Faisal Wani, Sittipong Sripaisarnmongkol, Kunat Pipatanakul

llms agents multimodal benchmarks

Related stories