12 papers
HINTT Submission to the 2nd MLC-SLM Challenge: Comparing Cascaded and Unified Approaches to Diarization and ASR
Takanori Ashihara, Kohei Matsuura, Masato Mimura
This paper presents the HINTT system submitted to the 2nd Challenge and Workshop on Multilingual Conversational Speech Language Model (MLC-SLM). We address multilingual speaker-att…
Improving Large-Scale Weakly Supervised ASR by Filtering and Selection
Kohei Matsuura, Masato Mimura
Leveraging large-scale weakly supervised datasets is crucial to train robust end-to-end automatic speech recognition (ASR) models. However, such datasets often contain noisy labels…
Progressive Alignment Objectives for Aligner-Encoder based ASR
Jaeyoung Lee, Masato Mimura, Takafumi Moriya
Aligner-Encoders are recently proposed seq2seq end-to-end ASR models that replace decoder attention by predicting the uth token directly from the u-th encoder position, so the enco…
Chunkwise Aligners for Streaming Speech Recognition
Wen Shen Teo, Takafumi Moriya, Masato Mimura
We propose the Chunkwise Aligner, a novel architecture for streaming automatic speech recognition (ASR). While the Transducer is the standard model for streaming ASR, its training…
Decoder-only Conformer with Modality-aware Sparse Mixtures of Experts for ASR
Jaeyoung Lee, Masato Mimura
We present a decoder-only Conformer for automatic speech recognition (ASR) that processes speech and text in a single stack without external speech encoders or pretrained large lan…
All-in-One ASR: Unifying Encoder-Decoder Models of CTC, Attention, and Transducer in Dual-Mode ASR
Takafumi Moriya, Masato Mimura, Tomohiro Tanaka +3
This paper proposes a unified framework, All-in-One ASR, that allows a single model to support multiple automatic speech recognition (ASR) paradigms, including connectionist tempor…
Microphone Array Geometry Independent Multi-Talker Distant ASR: NTT System for the DASR Task of the CHiME-8 Challenge
Naoyuki Kamo, Naohiro Tawara, Atsushi Ando +15
In this paper, we introduce a multi-talker distant automatic speech recognition (DASR) system we designed for the DASR task 1 of the CHiME-8 challenge. Our system performs speaker…
Boosting Hybrid Autoregressive Transducer-based ASR with Internal Acoustic Model Training and Dual Blank Thresholding
Takafumi Moriya, Takanori Ashihara, Masato Mimura +4
A hybrid autoregressive transducer (HAT) is a variant of neural transducer that models blank and non-blank posterior distributions separately. In this paper, we propose a novel int…
Alignment-Free Training for Transducer-based Multi-Talker ASR
Takafumi Moriya, Shota Horiguchi, Marc Delcroix +5
Extending the RNN Transducer (RNNT) to recognize multi-talker speech is essential for wider automatic speech recognition (ASR) applications. Multi-talker RNNT (MT-RNNT) aims to ach…
NTT Multi-Speaker ASR System for the DASR Task of CHiME-8 Challenge
Naoyuki Kamo, Naohiro Tawara, Atsushi Ando +15
We present a distant automatic speech recognition (DASR) system developed for the CHiME-8 DASR track. It consists of a diarization first pipeline. For diarization, we use end-to-en…
Sentence-wise Speech Summarization: Task, Datasets, and End-to-End Modeling with LM Knowledge Distillation
Kohei Matsuura, Takanori Ashihara, Takafumi Moriya +4
This paper introduces a novel approach called sentence-wise speech summarization (Sen-SSum), which generates text summaries from a spoken document in a sentence-by-sentence manner.…
SpeakerBeam-SS: Real-time Target Speaker Extraction with Lightweight Conv-TasNet and State Space Modeling
Hiroshi Sato, Takafumi Moriya, Masato Mimura +6
Real-time target speaker extraction (TSE) is intended to extract the desired speaker's voice from the observed mixture of multiple speakers in a streaming manner. Implementing real…