198 citations · 281 across the 14 of their papers we have counts for
12 papers · 1 filter
Pushing the Boundaries of Streaming Multi-Speaker ASR: A Systematic Study of Architectural Trade-offs
Taejin Park, Ivan Medennikov, Kunal Dhawan +3
Streaming multi-speaker ASR is a challenging task that must balance accuracy, latency, and efficiency while handling overlapping speech and maintaining coherent long-context modeli…
Streaming Sortformer: Speaker Cache-Based Online Speaker Diarization with Arrival-Time Ordering
Ivan Medennikov, Taejin Park, Weiqing Wang +5
This paper presents a streaming extension for the Sortformer speaker diarization framework, whose key property is the arrival-time ordering of output speakers. The proposed approac…
Speaker Targeting via Self-Speaker Adaptation for Multi-talker ASR
Weiqing Wang, Taejin Park, Ivan Medennikov +6
We propose a self-speaker adaptation method for streaming multi-talker automatic speech recognition (ASR) that eliminates the need for explicit speaker queries. Unlike conventional…
META-CAT: Speaker-Informed Speech Embeddings via Meta Information Concatenation for Multi-talker ASR
Jinhan Wang, Weiqing Wang, Kunal Dhawan +7
We propose a novel end-to-end multi-talker automatic speech recognition (ASR) framework that enables both multi-speaker (MS) ASR and target-speaker (TS) ASR. Our proposed model is…
Sortformer: A Novel Approach for Permutation-Resolved Speaker Supervision in Speech-to-Text Systems
Taejin Park, Ivan Medennikov, Kunal Dhawan +6
Sortformer is an encoder-based speaker diarization model designed for supervising speaker tagging in speech-to-text models. Instead of relying solely on permutation invariant loss…
Resource-Efficient Adaptation of Speech Foundation Models for Multi-Speaker ASR
Weiqing Wang, Kunal Dhawan, Taejin Park +6
Speech foundation models have achieved state-of-the-art (SoTA) performance across various tasks, such as automatic speech recognition (ASR) in hundreds of languages. However, multi…
LT-LM: a novel non-autoregressive language model for single-shot lattice rescoring
Anton Mitrofanov, Mariya Korenevskaya, Ivan Podluzhny +7
Neural network-based language models are commonly used in rescoring approaches to improve the quality of modern automatic speech recognition (ASR) systems. Most of the existing met…
Dynamic Acoustic Unit Augmentation With BPE-Dropout for Low-Resource End-to-End Speech Recognition
Aleksandr Laptev, Andrei Andrusenko, Ivan Podluzhny +3
With the rapid development of speech assistants, adapting server-intended automatic speech recognition (ASR) solutions to a direct device has become crucial. Researchers and indust…
Exploration of End-to-End ASR for OpenSTT -- Russian Open Speech-to-Text Dataset
Andrei Andrusenko, Aleksandr Laptev, Ivan Medennikov
This paper presents an exploration of end-to-end automatic speech recognition systems (ASR) for the largest open-source Russian language data set -- OpenSTT. We evaluate different…
Target-Speaker Voice Activity Detection: a Novel Approach for Multi-Speaker Diarization in a Dinner Party Scenario
Ivan Medennikov, Maxim Korenevsky, Tatiana Prisyach +9
Speaker diarization for real-life scenarios is an extremely challenging problem. Widely used clustering-based diarization approaches perform rather poorly in such conditions, mainl…
You Do Not Need More Data: Improving End-To-End Speech Recognition by Text-To-Speech Data Augmentation
Aleksandr Laptev, Roman Korostik, Aleksey Svischev +3
Data augmentation is one of the most effective ways to make end-to-end automatic speech recognition (ASR) perform close to the conventional hybrid approach, especially when dealing…
Towards a Competitive End-to-End Speech Recognition for CHiME-6 Dinner Party Transcription
Andrei Andrusenko, Aleksandr Laptev, Ivan Medennikov
While end-to-end ASR systems have proven competitive with the conventional hybrid approach, they are prone to accuracy degradation when it comes to noisy and low-resource condition…