activity
20192026
most citedIterative Pseudo-Labeling for Speech Recognition

27 citations · 35 across the 11 of their papers we have counts for

collaborators

18 papers

cs.LG2026

Path-Constrained Mixture-of-Experts

Zijin Gu, Tatiana Likhomanenko, Vimal Thilak +2

Sparse Mixture-of-Experts (MoE) architectures route each token through a subset of experts at each layer independently. We propose viewing MoE computation through the lens of \emph…

cs.SD2026

Which Data Matter? Embedding-Based Data Selection for Speech Recognition

Zakaria Aldeneh, Skyler Seto, Maureen de Seyssel +8

Modern ASR systems are typically trained on large-scale pseudo-labeled, in-the-wild data spanning multiple domains. While such heterogeneous data benefit generalist models designed…

cs.CL2025

Closing the Gap Between Text and Speech Understanding in LLMs

Santiago Cuervo, Skyler Seto, Maureen de Seyssel +5

Large Language Models (LLMs) can be adapted to extend their text capabilities to speech inputs. However, these speech-adapted LLMs consistently underperform their text-based counte…

cs.CL2025

Omni-Router: Sharing Routing Decisions in Sparse Mixture-of-Experts for Speech Recognition

Zijin Gu, Tatiana Likhomanenko, Navdeep Jaitly

Mixture-of-experts (MoE) architectures have expanded from language modeling to automatic speech recognition (ASR). Traditional MoE methods, such as the Switch Transformer, route ex…

cs.CL2025

SpeakStream: Streaming Text-to-Speech with Interleaved Data

Richard He Bai, Zijin Gu, Tatiana Likhomanenko +1

The latency bottleneck of traditional text-to-speech (TTS) systems fundamentally hinders the potential of streaming large language models (LLMs) in conversational AI. These TTS sys…

cs.MM2024

Mechanisms of Multimodal Synchronization: Insights from Decoder-Based Video-Text-to-Speech Synthesis

Akshita Gupta, Tatiana Likhomanenko, Karren Dai Yang +3

Unified decoder-only transformers have shown promise for multimodal generation, yet the mechanisms by which they synchronize modalities with heterogeneous sampling rates remain und…