papers

Publications (19)

cs.SD2026

NaijaS2ST: A Multi-Accent Benchmark for Speech-to-Speech Translation in Low-Resource Nigerian Languages

Marie Maltais, Yejin Jeon, Min Ma +7

Speech translation for low-resource languages remains fundamentally limited by the scarcity of high-quality, diverse parallel speech data, a challenge that is especially pronounced…

cs.CL2022

FLEURS: Few-shot Learning Evaluation of Universal Representations of Speech

Alexis Conneau, Min Ma, Simran Khanuja +6

We introduce FLEURS, the Few-shot Learning Evaluation of Universal Representations of Speech benchmark. FLEURS is an n-way parallel speech dataset in 102 languages built on top of…

cs.CL2025

Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities

Gheorghe Comanici, Eric Bieber, Mike Schaekermann +3431

In this report, we introduce the Gemini 2.X model family: Gemini 2.5 Pro and Gemini 2.5 Flash, as well as our earlier Gemini 2.0 Flash and Flash-Lite models. Gemini 2.5 Pro is our…

cs.CL2023

Label Aware Speech Representation Learning For Language Identification

Shikhar Vashishth, Shikhar Bharadwaj, Sriram Ganapathy +5

Speech representation learning approaches for non-semantic tasks such as language recognition have either explored supervised embedding extraction methods using a classifier model…

eess.SY2024

Finite-Time Adaptive Fuzzy Tracking Control for Nonlinear State Constrained Pure-Feedback Systems

Ju Wu, Tong Wang, Min Ma

This paper investigates the finite-time adaptive fuzzy tracking control problem for a class of pure-feedback system with full-state constraints. With the help of Mean-Value Theorem…

cs.SD2021

Improving Streaming Automatic Speech Recognition With Non-Streaming Model Distillation On Unsupervised Data

Thibault Doutre, Wei Han, Min Ma +7

Streaming end-to-end automatic speech recognition (ASR) models are widely used on smart speakers and on-device applications. Since these models are expected to transcribe speech wi…

cs.CL2025

Gemma 3 Technical Report

Gemma Team, Aishwarya Kamath, Johan Ferret +209

We introduce Gemma 3, a multimodal addition to the Gemma family of lightweight open models, ranging in scale from 1 to 27 billion parameters. This version introduces vision underst…

eess.AS2022

BigSSL: Exploring the Frontier of Large-Scale Semi-Supervised Learning for Automatic Speech Recognition

Yu Zhang, Daniel S. Park, Wei Han +23

We summarize the results of a host of efforts using giant automatic speech recognition (ASR) models pre-trained using large, diverse unlabeled datasets containing approximately a m…

cs.CL2022

XTREME-S: Evaluating Cross-lingual Speech Representations

Alexis Conneau, Ankur Bapna, Yu Zhang +16

We introduce XTREME-S, a new benchmark to evaluate universal cross-lingual speech representations in many languages. XTREME-S covers four task families: speech recognition, classif…

cs.CL2026

Gemma 4 Technical Report

Gemma Team, Sherif El Abd, Vaibhav Aggarwal +320

We introduce Gemma 4, a new generation of open-weight, natively multimodal language models in the Gemma model family. Designed to advance compute efficiency and reasoning, the Gemm…

cs.LG2026

How Transparent is DiffusionGemma?

Joshua Engels, Callum McDougall, Bilal Chughtai +11

LLM reasoning transparency is a critical affordance for understanding model decisions, mitigating misuse and misalignment, and debugging surprising model behaviors. However, Diffus…

cs.CL2023

Multimodal Modeling For Spoken Language Identification

Shikhar Bharadwaj, Min Ma, Shikhar Vashishth +10

Spoken language identification refers to the task of automatically predicting the spoken language in a given utterance. Conventionally, it is modeled as a speech-based language ide…

cs.CL2025

Encoder-Decoder Gemma: Improving the Quality-Efficiency Trade-Off via Adaptation

Biao Zhang, Fedor Moiseev, Joshua Ainslie +7

While decoder-only large language models (LLMs) have shown impressive results, encoder-decoder models are still widely adopted in real-world applications for their inference effici…

cs.CL2024

FLEURS-R: A Restored Multilingual Speech Corpus for Generation Tasks

Min Ma, Yuma Koizumi, Shigeki Karita +4

This paper introduces FLEURS-R, a speech restoration applied version of the Few-shot Learning Evaluation of Universal Representations of Speech (FLEURS) corpus. FLEURS-R maintains…

cs.SD2023

MASR: Multi-label Aware Speech Representation

Anjali Raj, Shikhar Bharadwaj, Sriram Ganapathy +2

In the recent years, speech representation learning is constructed primarily as a self-supervised learning (SSL) task, using the raw audio signal alone, while ignoring the side-inf…

cs.CL2025

mSTEB: Massively Multilingual Evaluation of LLMs on Speech and Text Tasks

Luel Hagos Beyene, Vivek Verma, Min Ma +4

Large Language models (LLMs) have demonstrated impressive performance on a wide range of tasks, including in multimodal settings such as speech. However, their evaluation is often…

cs.CL2023

XTREME-UP: A User-Centric Scarce-Data Benchmark for Under-Represented Languages

Sebastian Ruder, Jonathan H. Clark, Alexander Gutkin +24

Data scarcity is a crucial issue for the development of highly multilingual NLP systems. Yet for many under-represented languages (ULs) -- languages for which NLP re-search is part…

cs.CL2021

Scaling End-to-End Models for Large-Scale Multilingual ASR

Bo Li, Ruoming Pang, Tara N. Sainath +7

Building ASR models across many languages is a challenging multi-task learning problem due to large variations and heavily unbalanced data. Existing work has shown positive transfe…

cs.CL2025

Encoder-Decoder or Decoder-Only? Revisiting Encoder-Decoder Large Language Model

Biao Zhang, Yong Cheng, Siamak Shakeri +3

Recent large language model (LLM) research has undergone an architectural shift from encoder-decoder modeling to nowadays the dominant decoder-only modeling. This rapid transition,…