activity
20242026
collaborators
Showing cs.CLShow all

6 papers · 1 filter

cs.CL2026

Preference-ASR: A Preference-Aware Test Set for Benchmarking ASR in the Era of Speech LLMs

Nithin Rao Koluguri, Sasha Meister, Nikolay Karpov +4

Popular ASR test sets adopt inconsistent conventions for numbers, disfluencies, entities, and casing, while standard normalizers erase the format distinctions users care about. Cur…

cs.CL2026

Open ASR Leaderboard: Towards Reproducible and Transparent Multilingual and Long-Form Speech Recognition Evaluation

Vaibhav Srivastav, Steven Zheng, Eric Bezzam +6

We present the Open ASR Leaderboard, a reproducible benchmarking platform with community contributions from academia and industry. It compares 86 open-source and proprietary system…

cs.CL2025

Canary-1B-v2 & Parakeet-TDT-0.6B-v3: Efficient and High-Performance Models for Multilingual ASR and AST

Monica Sekoyan, Nithin Rao Koluguri, Nune Tadevosyan +5

This report introduces Canary-1B-v2, a fast, robust multilingual model for Automatic Speech Recognition (ASR) and Speech-to-Text Translation (AST). Built with a FastConformer encod…

cs.CL2025

Granary: Speech Recognition and Translation Dataset in 25 European Languages

Nithin Rao Koluguri, Monica Sekoyan, George Zelenfroynd +12

Multi-task and multilingual approaches benefit large models, yet speech processing for low-resource languages remains underexplored due to data scarcity. To address this, we presen…

cs.CL2025

Training and Inference Efficiency of Encoder-Decoder Speech Models

Piotr Żelasko, Kunal Dhawan, Daniel Galvez +7

Attention encoder-decoder model architecture is the backbone of several recent top performing foundation speech models: Whisper, Seamless, OWSM, and Canary-1B. However, the reporte…

cs.CL2024

BESTOW: Efficient and Streamable Speech Language Model with the Best of Two Worlds in GPT and T5

Zhehuai Chen, He Huang, Oleksii Hrinchuk +5

Incorporating speech understanding capabilities into pretrained large-language models has become a vital research direction (SpeechLLM). The previous architectures can be categoriz…