92 citations · 429 across the 49 of their papers we have counts for
49 papers
Diarization Error Decomposition Under Pause Annotation Ambiguity
Shota Horiguchi, Marc Delcroix, Naohiro Tawara +1
Speaker diarization evaluation is sensitive to ambiguity in pause annotation, which can inflate diarization error rate (DER) or obscure genuine model errors. We show that morpholog…
Over-Tightening-Aware Pseudo-Labeling for Tight-Boundary Speaker Diarization
Shota Horiguchi, Takanori Ashihara, Marc Delcroix +2
Training speaker diarization models on loose labels, such as speech segments with padded boundaries or filled pauses, often results in similarly loose model outputs. To obtain tigh…
Tight Boundary Prediction in Speaker Diarization Using Causal-Anticausal Consistency
Shota Horiguchi, Marc Delcroix, Naohiro Tawara +2
Multi-talker conversational automatic speech recognition data are often used to train speaker diarization models. Because such data prioritize semantic continuity, pauses and bound…
Frontend Token Enhancement for Token-Based Speech Recognition
Takanori Ashihara, Shota Horiguchi, Kohei Matsuura +2
Discretized representations of speech signals are efficient alternatives to continuous features for various speech applications, including automatic speech recognition (ASR) and sp…
Can We Really Repurpose Multi-Speaker ASR Corpus for Speaker Diarization?
Shota Horiguchi, Naohiro Tawara, Takanori Ashihara +2
Neural speaker diarization is widely used for overlap-aware speaker diarization, but it requires large multi-speaker datasets for training. To meet this data requirement, large dat…
Mitigating Non-Target Speaker Bias in Guided Speaker Embedding
Shota Horiguchi, Takanori Ashihara, Marc Delcroix +2
Obtaining high-quality speaker embeddings in multi-speaker conditions is crucial for many applications. A recently proposed guided speaker embedding framework, which utilizes speec…
Dissecting the Segmentation Model of End-to-End Diarization with Vector Clustering
Alexis Plaquet, Naohiro Tawara, Marc Delcroix +4
End-to-End Neural Diarization with Vector Clustering is a powerful and practical approach to perform Speaker Diarization. Multiple enhancements have been proposed for the segmentat…
Voice Impression Control in Zero-Shot TTS
Kenichi Fujita, Shota Horiguchi, Yusuke Ijima
Para-/non-linguistic information in speech is pivotal in shaping the listeners' impression. Although zero-shot text-to-speech (TTS) has achieved high speaker fidelity, modulating s…
Pretraining Multi-Speaker Identification for Neural Speaker Diarization
Shota Horiguchi, Atsushi Ando, Marc Delcroix +1
End-to-end speaker diarization enables accurate overlap-aware diarization by jointly estimating multiple speakers' speech activities in parallel. This approach is data-hungry, requ…
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…
Investigation of Speaker Representation for Target-Speaker Speech Processing
Takanori Ashihara, Takafumi Moriya, Shota Horiguchi +5
Target-speaker speech processing (TS) tasks, such as target-speaker automatic speech recognition (TS-ASR), target speech extraction (TSE), and personal voice activity detection (p-…
Mamba-based Segmentation Model for Speaker Diarization
Alexis Plaquet, Naohiro Tawara, Marc Delcroix +3
Mamba is a newly proposed architecture which behaves like a recurrent neural network (RNN) with attention-like capabilities. These properties are promising for speaker diarization,…
Guided Speaker Embedding
Shota Horiguchi, Takafumi Moriya, Atsushi Ando +4
This paper proposes a guided speaker embedding extraction system, which extracts speaker embeddings of the target speaker using speech activities of target and interference speaker…
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…
Recursive Attentive Pooling for Extracting Speaker Embeddings from Multi-Speaker Recordings
Shota Horiguchi, Atsushi Ando, Takafumi Moriya +4
This paper proposes a method for extracting speaker embedding for each speaker from a variable-length recording containing multiple speakers. Speaker embeddings are crucial not onl…
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…
Factor-Conditioned Speaking-Style Captioning
Atsushi Ando, Takafumi Moriya, Shota Horiguchi +1
This paper presents a novel speaking-style captioning method that generates diverse descriptions while accurately predicting speaking-style information. Conventional learning crite…
Thresholding Data Shapley for Data Cleansing Using Multi-Armed Bandits
Hiroyuki Namba, Shota Horiguchi, Masaki Hamamoto +1
Data cleansing aims to improve model performance by removing a set of harmful instances from the training dataset. Data Shapley is a common theoretically guaranteed method to evalu…
Streaming Active Learning for Regression Problems Using Regression via Classification
Shota Horiguchi, Kota Dohi, Yohei Kawaguchi
One of the challenges in deploying a machine learning model is that the model's performance degrades as the operating environment changes. To maintain the performance, streaming ac…
CAPTDURE: Captioned Sound Dataset of Single Sources
Yuki Okamoto, Kanta Shimonishi, Keisuke Imoto +3
In conventional studies on environmental sound separation and synthesis using captions, datasets consisting of multiple-source sounds with their captions were used for model traini…
Spoofing Attacker Also Benefits from Self-Supervised Pretrained Model
Aoi Ito, Shota Horiguchi
Large-scale pretrained models using self-supervised learning have reportedly improved the performance of speech anti-spoofing. However, the attacker side may also make use of such…
Mutual Learning of Single- and Multi-Channel End-to-End Neural Diarization
Shota Horiguchi, Yuki Takashima, Shinji Watanabe +1
Due to the high performance of multi-channel speech processing, we can use the outputs from a multi-channel model as teacher labels when training a single-channel model with knowle…
Updating Only Encoders Prevents Catastrophic Forgetting of End-to-End ASR Models
Yuki Takashima, Shota Horiguchi, Shinji Watanabe +2
In this paper, we present an incremental domain adaptation technique to prevent catastrophic forgetting for an end-to-end automatic speech recognition (ASR) model. Conventional app…