Shota Horiguchi

Shota Horiguchi, Shinji Watanabe, Paola Garcia et al.

A method to perform offline and online speaker diarization for an unlimited number of speakers is described in this paper. End-to-end neural diarization (EEND) has achieved overlap-aware speaker diarization by formulating it as a multi-label classification problem. It has also been extended for a flexible number of speakers by introducing speaker-wise attractors. However, the output number of speakers of attractor-based EEND is empirically capped; it cannot deal with cases where the number of speakers appearing during inference is higher than that during training because its speaker counting is trained in a fully supervised manner. Our method, EEND-GLA, solves this problem by introducing unsupervised clustering into attractor-based EEND. In the method, the input audio is first divided into short blocks, then attractor-based diarization is performed for each block, and finally, the results of each block are clustered on the basis of the similarity between locally-calculated attractors. While the number of output speakers is limited within each block, the total number of speakers estimated for the entire input can be higher than the limitation. To use EEND-GLA in an online manner, our method also extends the speaker-tracing buffer, which was originally proposed to enable online inference of conventional EEND. We introduce a block-wise buffer update to make the speaker-tracing buffer compatible with EEND-GLA. Finally, to improve online diarization, our method improves the buffer update method and revisits the variable chunk-size training of EEND. The experimental results demonstrate that EEND-GLA can perform speaker diarization of an unseen number of speakers in both offline and online inferences.

Shota Horiguchi, Yuki Takashima, Shinji Watanabe et al.

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 knowledge distillation. To the contrary, it is also known that single-channel speech data can benefit multi-channel models by mixing it with multi-channel speech data during training or by using it for model pretraining. This paper focuses on speaker diarization and proposes to conduct the above bi-directional knowledge transfer alternately. We first introduce an end-to-end neural diarization model that can handle both single- and multi-channel inputs. Using this model, we alternately conduct i) knowledge distillation from a multi-channel model to a single-channel model and ii) finetuning from the distilled single-channel model to a multi-channel model. Experimental results on two-speaker data show that the proposed method mutually improved single- and multi-channel speaker diarization performances.

Takafumi Moriya, Shota Horiguchi, Marc Delcroix et al.

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 achieve recognition without relying on costly front-end source separation. MT-RNNT is conventionally implemented using architectures with multiple encoders or decoders, or by serializing all speakers' transcriptions into a single output stream. The first approach is computationally expensive, particularly due to the need for multiple encoder processing. In contrast, the second approach involves a complex label generation process, requiring accurate timestamps of all words spoken by all speakers in the mixture, obtained from an external ASR system. In this paper, we propose a novel alignment-free training scheme for the MT-RNNT (MT-RNNT-AFT) that adopts the standard RNNT architecture. The target labels are created by appending a prompt token corresponding to each speaker at the beginning of the transcription, reflecting the order of each speaker's appearance in the mixtures. Thus, MT-RNNT-AFT can be trained without relying on accurate alignments, and it can recognize all speakers' speech with just one round of encoder processing. Experiments show that MT-RNNT-AFT achieves performance comparable to that of the state-of-the-art alternatives, while greatly simplifying the training process.

Natsuo Yamashita, Shota Horiguchi, Takeshi Homma

This paper investigates a method for simulating natural conversation in the model training of end-to-end neural diarization (EEND). Due to the lack of any annotated real conversational dataset, EEND is usually pretrained on a large-scale simulated conversational dataset first and then adapted to the target real dataset. Simulated datasets play an essential role in the training of EEND, but as yet there has been insufficient investigation into an optimal simulation method. We thus propose a method to simulate natural conversational speech. In contrast to conventional methods, which simply combine the speech of multiple speakers, our method takes turn-taking into account. We define four types of speaker transition and sequentially arrange them to simulate natural conversations. The dataset simulated using our method was found to be statistically similar to the real dataset in terms of the silence and overlap ratios. The experimental results on two-speaker diarization using the CALLHOME and CSJ datasets showed that the simulated dataset contributes to improving the performance of EEND.

Takanori Ashihara, Shota Horiguchi, Kohei Matsuura et al.

Discretized representations of speech signals are efficient alternatives to continuous features for various speech applications, including automatic speech recognition (ASR) and speech language models. However, these representations, such as semantic or phonetic tokens derived from clustering outputs of self-supervised learning (SSL) speech models, are susceptible to environmental noise, which can degrade backend task performance. In this work, we introduce a frontend system that estimates clean speech tokens from noisy speech and evaluate it on an ASR backend using semantic tokens. We consider four types of enhancement models based on their input/output domains: wave-to-wave, token-to-token, continuous SSL features-to-token, and wave-to-token. These models are trained independently of ASR backends. Experiments on the CHiME-4 dataset demonstrate that wave-to-token enhancement achieves the best performance among the frontends. Moreover, it mostly outperforms the ASR system based on continuous SSL features.

Terufumi Morishita, Gaku Morio, Shota Horiguchi et al.

We propose a fundamental theory on ensemble learning that answers the central question: what factors make an ensemble system good or bad? Previous studies used a variant of Fano's inequality of information theory and derived a lower bound of the classification error rate on the basis of the $\textit{accuracy}$ and $\textit{diversity}$ of models. We revisit the original Fano's inequality and argue that the studies did not take into account the information lost when multiple model predictions are combined into a final prediction. To address this issue, we generalize the previous theory to incorporate the information loss, which we name $\textit{combination loss}$. Further, we empirically validate and demonstrate the proposed theory through extensive experiments on actual systems. The theory reveals the strengths and weaknesses of systems on each metric, which will push the theoretical understanding of ensemble learning and give us insights into designing systems.

Shinji Watanabe, Michael Mandel, Jon Barker et al.

Following the success of the 1st, 2nd, 3rd, 4th and 5th CHiME challenges we organize the 6th CHiME Speech Separation and Recognition Challenge (CHiME-6). The new challenge revisits the previous CHiME-5 challenge and further considers the problem of distant multi-microphone conversational speech diarization and recognition in everyday home environments. Speech material is the same as the previous CHiME-5 recordings except for accurate array synchronization. The material was elicited using a dinner party scenario with efforts taken to capture data that is representative of natural conversational speech. This paper provides a baseline description of the CHiME-6 challenge for both segmented multispeaker speech recognition (Track 1) and unsegmented multispeaker speech recognition (Track 2). Of note, Track 2 is the first challenge activity in the community to tackle an unsegmented multispeaker speech recognition scenario with a complete set of reproducible open source baselines providing speech enhancement, speaker diarization, and speech recognition modules.

Yusuke Fujita, Naoyuki Kanda, Shota Horiguchi et al.

Speaker diarization has been mainly developed based on the clustering of speaker embeddings. However, the clustering-based approach has two major problems; i.e., (i) it is not optimized to minimize diarization errors directly, and (ii) it cannot handle speaker overlaps correctly. To solve these problems, the End-to-End Neural Diarization (EEND), in which a bidirectional long short-term memory (BLSTM) network directly outputs speaker diarization results given a multi-talker recording, was recently proposed. In this study, we enhance EEND by introducing self-attention blocks instead of BLSTM blocks. In contrast to BLSTM, which is conditioned only on its previous and next hidden states, self-attention is directly conditioned on all the other frames, making it much suitable for dealing with the speaker diarization problem. We evaluated our proposed method on simulated mixtures, real telephone calls, and real dialogue recordings. The experimental results revealed that the self-attention was the key to achieving good performance and that our proposed method performed significantly better than the conventional BLSTM-based method. Our method was even better than that of the state-of-the-art x-vector clustering-based method. Finally, by visualizing the latent representation, we show that the self-attention can capture global speaker characteristics in addition to local speech activity dynamics. Our source code is available online at https://github.com/hitachi-speech/EEND.

Yusuke Fujita, Naoyuki Kanda, Shota Horiguchi et al.

In this paper, we propose a novel end-to-end neural-network-based speaker diarization method. Unlike most existing methods, our proposed method does not have separate modules for extraction and clustering of speaker representations. Instead, our model has a single neural network that directly outputs speaker diarization results. To realize such a model, we formulate the speaker diarization problem as a multi-label classification problem, and introduces a permutation-free objective function to directly minimize diarization errors without being suffered from the speaker-label permutation problem. Besides its end-to-end simplicity, the proposed method also benefits from being able to explicitly handle overlapping speech during training and inference. Because of the benefit, our model can be easily trained/adapted with real-recorded multi-speaker conversations just by feeding the corresponding multi-speaker segment labels. We evaluated the proposed method on simulated speech mixtures. The proposed method achieved diarization error rate of 12.28%, while a conventional clustering-based system produced diarization error rate of 28.77%. Furthermore, the domain adaptation with real-recorded speech provided 25.6% relative improvement on the CALLHOME dataset. Our source code is available online at https://github.com/hitachi-speech/EEND.

Takanori Ashihara, Takafumi Moriya, Shota Horiguchi et al.

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-VAD), are important for extracting information about a desired speaker's speech even when it is corrupted by interfering speakers. While most studies have focused on training schemes or system architectures for each specific task, the auxiliary network for embedding target-speaker cues has not been investigated comprehensively in a unified cross-task evaluation. Therefore, this paper aims to address a fundamental question: what is the preferred speaker embedding for TS tasks? To this end, for the TS-ASR, TSE, and p-VAD tasks, we compare pre-trained speaker encoders (i.e., self-supervised or speaker recognition models) that compute speaker embeddings from pre-recorded enrollment speech of the target speaker with ideal speaker embeddings derived directly from the target speaker's identity in the form of a one-hot vector. To further understand the properties of ideal speaker embedding, we optimize it using a gradient-based approach to improve performance on the TS task. Our analysis reveals that speaker verification performance is somewhat unrelated to TS task performances, the one-hot vector outperforms enrollment-based ones, and the optimal embedding depends on the input mixture.

Hiroyuki Namba, Shota Horiguchi, Masaki Hamamoto et al.

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 evaluate the contribution of each instance to model performance; however, it requires training on all subsets of the training data, which is computationally expensive. In this paper, we propose an iterativemethod to fast identify a subset of instances with low data Shapley values by using the thresholding bandit algorithm. We provide a theoretical guarantee that the proposed method can accurately select harmful instances if a sufficiently large number of iterations is conducted. Empirical evaluation using various models and datasets demonstrated that the proposed method efficiently improved the computational speed while maintaining the model performance.

Atsushi Ando, Takafumi Moriya, Shota Horiguchi et al.

This paper presents a novel speaking-style captioning method that generates diverse descriptions while accurately predicting speaking-style information. Conventional learning criteria directly use original captions that contain not only speaking-style factor terms but also syntax words, which disturbs learning speaking-style information. To solve this problem, we introduce factor-conditioned captioning (FCC), which first outputs a phrase representing speaking-style factors (e.g., gender, pitch, etc.), and then generates a caption to ensure the model explicitly learns speaking-style factors. We also propose greedy-then-sampling (GtS) decoding, which first predicts speaking-style factors deterministically to guarantee semantic accuracy, and then generates a caption based on factor-conditioned sampling to ensure diversity. Experiments show that FCC outperforms the original caption-based training, and with GtS, it generates more diverse captions while keeping style prediction performance.

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 active learning is used, in which the model is retrained by adding a newly annotated sample to the training dataset if the prediction of the sample is not certain enough. Although many streaming active learning methods have been proposed for classification, few efforts have been made for regression problems, which are often handled in the industrial field. In this paper, we propose to use the regression-via-classification framework for streaming active learning for regression. Regression-via-classification transforms regression problems into classification problems so that streaming active learning methods proposed for classification problems can be applied directly to regression problems. Experimental validation on four real data sets shows that the proposed method can perform regression with higher accuracy at the same annotation cost.

Yuki Okamoto, Shota Horiguchi, Masaaki Yamamoto et al.

An onomatopoeic word, which is a character sequence that phonetically imitates a sound, is effective in expressing characteristics of sound such as duration, pitch, and timbre. We propose an environmental-sound-extraction method using onomatopoeic words to specify the target sound to be extracted. By this method, we estimate a time-frequency mask from an input mixture spectrogram and an onomatopoeic word using a U-Net architecture, then extract the corresponding target sound by masking the spectrogram. Experimental results indicate that the proposed method can extract only the target sound corresponding to the onomatopoeic word and performs better than conventional methods that use sound-event classes to specify the target sound.

Shota Horiguchi, Yuki Takashima, Paola Garcia et al.

Recent progress on end-to-end neural diarization (EEND) has enabled overlap-aware speaker diarization with a single neural network. This paper proposes to enhance EEND by using multi-channel signals from distributed microphones. We replace Transformer encoders in EEND with two types of encoders that process a multi-channel input: spatio-temporal and co-attention encoders. Both are independent of the number and geometry of microphones and suitable for distributed microphone settings. We also propose a model adaptation method using only single-channel recordings. With simulated and real-recorded datasets, we demonstrated that the proposed method outperformed conventional EEND when a multi-channel input was given while maintaining comparable performance with a single-channel input. We also showed that the proposed method performed well even when spatial information is inoperative given multi-channel inputs, such as in hybrid meetings in which the utterances of multiple remote participants are played back from the same loudspeaker.

Shota Horiguchi, Shinji Watanabe, Paola Garcia et al.

Attractor-based end-to-end diarization is achieving comparable accuracy to the carefully tuned conventional clustering-based methods on challenging datasets. However, the main drawback is that it cannot deal with the case where the number of speakers is larger than the one observed during training. This is because its speaker counting relies on supervised learning. In this work, we introduce an unsupervised clustering process embedded in the attractor-based end-to-end diarization. We first split a sequence of frame-wise embeddings into short subsequences and then perform attractor-based diarization for each subsequence. Given subsequence-wise diarization results, inter-subsequence speaker correspondence is obtained by unsupervised clustering of the vectors computed from the attractors from all the subsequences. This makes it possible to produce diarization results of a large number of speakers for the whole recording even if the number of output speakers for each subsequence is limited. Experimental results showed that our method could produce accurate diarization results of an unseen number of speakers. Our method achieved 11.84 %, 28.33 %, and 19.49 % on the CALLHOME, DIHARD II, and DIHARD III datasets, respectively, each of which is better than the conventional end-to-end diarization methods.

Shota Horiguchi, Yusuke Fujita, Shinji Watanabe et al.

This paper investigates an end-to-end neural diarization (EEND) method for an unknown number of speakers. In contrast to the conventional cascaded approach to speaker diarization, EEND methods are better in terms of speaker overlap handling. However, EEND still has a disadvantage in that it cannot deal with a flexible number of speakers. To remedy this problem, we introduce encoder-decoder-based attractor calculation module (EDA) to EEND. Once frame-wise embeddings are obtained, EDA sequentially generates speaker-wise attractors on the basis of a sequence-to-sequence method using an LSTM encoder-decoder. The attractor generation continues until a stopping condition is satisfied; thus, the number of attractors can be flexible. Diarization results are then estimated as dot products of the attractors and embeddings. The embeddings from speaker overlaps result in larger dot product values with multiple attractors; thus, this method can deal with speaker overlaps. Because the maximum number of output speakers is still limited by the training set, we also propose an iterative inference method to remove this restriction. Further, we propose a method that aligns the estimated diarization results with the results of an external speech activity detector, which enables fair comparison against cascaded approaches. Extensive evaluations on simulated and real datasets show that EEND-EDA outperforms the conventional cascaded approach.

Yuki Takashima, Yusuke Fujita, Shota Horiguchi et al.

In this paper, we present a semi-supervised training technique using pseudo-labeling for end-to-end neural diarization (EEND). The EEND system has shown promising performance compared with traditional clustering-based methods, especially in the case of overlapping speech. However, to get a well-tuned model, EEND requires labeled data for all the joint speech activities of every speaker at each time frame in a recording. In this paper, we explore a pseudo-labeling approach that employs unlabeled data. First, we propose an iterative pseudo-label method for EEND, which trains the model using unlabeled data of a target condition. Then, we also propose a committee-based training method to improve the performance of EEND. To evaluate our proposed method, we conduct the experiments of model adaptation using labeled and unlabeled data. Experimental results on the CALLHOME dataset show that our proposed pseudo-label achieved a 37.4% relative diarization error rate reduction compared to a seed model. Moreover, we analyzed the results of semi-supervised adaptation with pseudo-labeling. We also show the effectiveness of our approach on the third DIHARD dataset.

Yuki Takashima, Yusuke Fujita, Shinji Watanabe et al.

In this paper, we present a conditional multitask learning method for end-to-end neural speaker diarization (EEND). The EEND system has shown promising performance compared with traditional clustering-based methods, especially in the case of overlapping speech. In this paper, to further improve the performance of the EEND system, we propose a novel multitask learning framework that solves speaker diarization and a desired subtask while explicitly considering the task dependency. We optimize speaker diarization conditioned on speech activity and overlap detection that are subtasks of speaker diarization, based on the probabilistic chain rule. Experimental results show that our proposed method can leverage a subtask to effectively model speaker diarization, and outperforms conventional EEND systems in terms of diarization error rate.

Shota Horiguchi, Nelson Yalta, Paola Garcia et al.

This paper provides a detailed description of the Hitachi-JHU system that was submitted to the Third DIHARD Speech Diarization Challenge. The system outputs the ensemble results of the five subsystems: two x-vector-based subsystems, two end-to-end neural diarization-based subsystems, and one hybrid subsystem. We refine each system and all five subsystems become competitive and complementary. After the DOVER-Lap based system combination, it achieved diarization error rates of 11.58 % and 14.09 % in Track 1 full and core, and 16.94 % and 20.01 % in Track 2 full and core, respectively. With their results, we won second place in all the tasks of the challenge.

Yawen Xue, Shota Horiguchi, Yusuke Fujita et al.

We propose a streaming diarization method based on an end-to-end neural diarization (EEND) model, which handles flexible numbers of speakers and overlapping speech. In our previous study, the speaker-tracing buffer (STB) mechanism was proposed to achieve a chunk-wise streaming diarization using a pre-trained EEND model. STB traces the speaker information in previous chunks to map the speakers in a new chunk. However, it only worked with two-speaker recordings. In this paper, we propose an extended STB for flexible numbers of speakers, FLEX-STB. The proposed method uses a zero-padding followed by speaker-tracing, which alleviates the difference in the number of speakers between a buffer and a current chunk. We also examine buffer update strategies to select important frames for tracing multiple speakers. Experiments on CALLHOME and DIHARD II datasets show that the proposed method achieves comparable performance to the offline EEND method with 1-second latency. The results also show that our proposed method outperforms recently proposed chunk-wise diarization methods based on EEND (BW-EDA-EEND).

Shota Horiguchi, Paola Garcia, Yusuke Fujita et al.

This paper investigates the utilization of an end-to-end diarization model as post-processing of conventional clustering-based diarization. Clustering-based diarization methods partition frames into clusters of the number of speakers; thus, they typically cannot handle overlapping speech because each frame is assigned to one speaker. On the other hand, some end-to-end diarization methods can handle overlapping speech by treating the problem as multi-label classification. Although some methods can treat a flexible number of speakers, they do not perform well when the number of speakers is large. To compensate for each other's weakness, we propose to use a two-speaker end-to-end diarization method as post-processing of the results obtained by a clustering-based method. We iteratively select two speakers from the results and update the results of the two speakers to improve the overlapped region. Experimental results show that the proposed algorithm consistently improved the performance of the state-of-the-art methods across CALLHOME, AMI, and DIHARD II datasets.

Shota Horiguchi, Yusuke Fujita, Kenji Nagamatsu

We propose a block-online algorithm of guided source separation (GSS). GSS is a speech separation method that uses diarization information to update parameters of the generative model of observation signals. Previous studies have shown that GSS performs well in multi-talker scenarios. However, it requires a large amount of calculation time, which is an obstacle to the deployment of online applications. It is also a problem that the offline GSS is an utterance-wise algorithm so that it produces latency according to the length of the utterance. With the proposed algorithm, block-wise input samples and corresponding time annotations are concatenated with those in the preceding context and used to update the parameters. Using the context enables the algorithm to estimate time-frequency masks accurately only from one iteration of optimization for each block, and its latency does not depend on the utterance length but predetermined block length. It also reduces calculation cost by updating only the parameters of active speakers in each block and its context. Evaluation on the CHiME-6 corpus and a meeting corpus showed that the proposed algorithm achieved almost the same performance as the conventional offline GSS algorithm but with 32x faster calculation, which is sufficient for real-time applications.

Shota Horiguchi, Yusuke Fujita, Kenji Nagamatsu

A novel framework for meeting transcription using asynchronous microphones is proposed in this paper. It consists of audio synchronization, speaker diarization, utterance-wise speech enhancement using guided source separation, automatic speech recognition, and duplication reduction. Doing speaker diarization before speech enhancement enables the system to deal with overlapped speech without considering sampling frequency mismatch between microphones. Evaluation on our real meeting datasets showed that our framework achieved a character error rate (CER) of 28.7 % by using 11 distributed microphones, while a monaural microphone placed on the center of the table had a CER of 38.2 %. We also showed that our framework achieved CER of 21.8 %, which is only 2.1 percentage points higher than the CER in headset microphone-based transcription.

Yawen Xue, Shota Horiguchi, Yusuke Fujita et al.

This paper proposes a novel online speaker diarization algorithm based on a fully supervised self-attention mechanism (SA-EEND). Online diarization inherently presents a speaker's permutation problem due to the possibility to assign speaker regions incorrectly across the recording. To circumvent this inconsistency, we proposed a speaker-tracing buffer mechanism that selects several input frames representing the speaker permutation information from previous chunks and stores them in a buffer. These buffered frames are stacked with the input frames in the current chunk and fed into a self-attention network. Our method ensures consistent diarization outputs across the buffer and the current chunk by checking the correlation between their corresponding outputs. Additionally, we trained SA-EEND with variable chunk-sizes to mitigate the mismatch between training and inference introduced by the speaker-tracing buffer mechanism. Experimental results, including online SA-EEND and variable chunk-size, achieved DERs of 12.54% for CALLHOME and 20.77% for CSJ with 1.4s actual latency.

Yusuke Fujita, Shinji Watanabe, Shota Horiguchi et al.

Speaker diarization is an essential step for processing multi-speaker audio. Although an end-to-end neural diarization (EEND) method achieved state-of-the-art performance, it is limited to a fixed number of speakers. In this paper, we solve this fixed number of speaker issue by a novel speaker-wise conditional inference method based on the probabilistic chain rule. In the proposed method, each speaker's speech activity is regarded as a single random variable, and is estimated sequentially conditioned on previously estimated other speakers' speech activities. Similar to other sequence-to-sequence models, the proposed method produces a variable number of speakers with a stop sequence condition. We evaluated the proposed method on multi-speaker audio recordings of a variable number of speakers. Experimental results show that the proposed method can correctly produce diarization results with a variable number of speakers and outperforms the state-of-the-art end-to-end speaker diarization methods in terms of diarization error rate.

Shota Horiguchi, Yusuke Fujita, Shinji Watanabe et al.

End-to-end speaker diarization for an unknown number of speakers is addressed in this paper. Recently proposed end-to-end speaker diarization outperformed conventional clustering-based speaker diarization, but it has one drawback: it is less flexible in terms of the number of speakers. This paper proposes a method for encoder-decoder based attractor calculation (EDA), which first generates a flexible number of attractors from a speech embedding sequence. Then, the generated multiple attractors are multiplied by the speech embedding sequence to produce the same number of speaker activities. The speech embedding sequence is extracted using the conventional self-attentive end-to-end neural speaker diarization (SA-EEND) network. In a two-speaker condition, our method achieved a 2.69 % diarization error rate (DER) on simulated mixtures and a 8.07 % DER on the two-speaker subset of CALLHOME, while vanilla SA-EEND attained 4.56 % and 9.54 %, respectively. In unknown numbers of speakers conditions, our method attained a 15.29 % DER on CALLHOME, while the x-vector-based clustering method achieved a 19.43 % DER.

Yusuke Fujita, Shinji Watanabe, Shota Horiguchi et al.

The most common approach to speaker diarization is clustering of speaker embeddings. However, the clustering-based approach has a number of problems; i.e., (i) it is not optimized to minimize diarization errors directly, (ii) it cannot handle speaker overlaps correctly, and (iii) it has trouble adapting their speaker embedding models to real audio recordings with speaker overlaps. To solve these problems, we propose the End-to-End Neural Diarization (EEND), in which a neural network directly outputs speaker diarization results given a multi-speaker recording. To realize such an end-to-end model, we formulate the speaker diarization problem as a multi-label classification problem and introduce a permutation-free objective function to directly minimize diarization errors. Besides its end-to-end simplicity, the EEND method can explicitly handle speaker overlaps during training and inference. Just by feeding multi-speaker recordings with corresponding speaker segment labels, our model can be easily adapted to real conversations. We evaluated our method on simulated speech mixtures and real conversation datasets. The results showed that the EEND method outperformed the state-of-the-art x-vector clustering-based method, while it correctly handled speaker overlaps. We explored the neural network architecture for the EEND method, and found that the self-attention-based neural network was the key to achieving excellent performance. In contrast to conditioning the network only on its previous and next hidden states, as is done using bidirectional long short-term memory (BLSTM), self-attention is directly conditioned on all the frames. By visualizing the attention weights, we show that self-attention captures global speaker characteristics in addition to local speech activity dynamics, making it especially suitable for dealing with the speaker diarization problem.

Naoyuki Kanda, Shota Horiguchi, Yusuke Fujita et al.

This paper investigates the use of target-speaker automatic speech recognition (TS-ASR) for simultaneous speech recognition and speaker diarization of single-channel dialogue recordings. TS-ASR is a technique to automatically extract and recognize only the speech of a target speaker given a short sample utterance of that speaker. One obvious drawback of TS-ASR is that it cannot be used when the speakers in the recordings are unknown because it requires a sample of the target speakers in advance of decoding. To remove this limitation, we propose an iterative method, in which (i) the estimation of speaker embeddings and (ii) TS-ASR based on the estimated speaker embeddings are alternately executed. We evaluated the proposed method by using very challenging dialogue recordings in which the speaker overlap ratio was over 20%. We confirmed that the proposed method significantly reduced both the word error rate (WER) and diarization error rate (DER). Our proposed method combined with i-vector speaker embeddings ultimately achieved a WER that differed by only 2.1 % from that of TS-ASR given oracle speaker embeddings. Furthermore, our method can solve speaker diarization simultaneously as a by-product and achieved better DER than that of the conventional clustering-based speaker diarization method based on i-vector.

Naoyuki Kanda, Shota Horiguchi, Ryoichi Takashima et al.

In this paper, we propose a novel auxiliary loss function for target-speaker automatic speech recognition (ASR). Our method automatically extracts and transcribes target speaker's utterances from a monaural mixture of multiple speakers speech given a short sample of the target speaker. The proposed auxiliary loss function attempts to additionally maximize interference speaker ASR accuracy during training. This will regularize the network to achieve a better representation for speaker separation, thus achieving better accuracy on the target-speaker ASR. We evaluated our proposed method using two-speaker-mixed speech in various signal-to-interference-ratio conditions. We first built a strong target-speaker ASR baseline based on the state-of-the-art lattice-free maximum mutual information. This baseline achieved a word error rate (WER) of 18.06% on the test set while a normal ASR trained with clean data produced a completely corrupted result (WER of 84.71%). Then, our proposed loss further reduced the WER by 6.6% relative to this strong baseline, achieving a WER of 16.87%. In addition to the accuracy improvement, we also showed that the auxiliary output branch for the proposed loss can even be used for a secondary ASR for interference speakers' speech.

Naoyuki Kanda, Christoph Boeddeker, Jens Heitkaemper et al.

In this paper, we present Hitachi and Paderborn University's joint effort for automatic speech recognition (ASR) in a dinner party scenario. The main challenges of ASR systems for dinner party recordings obtained by multiple microphone arrays are (1) heavy speech overlaps, (2) severe noise and reverberation, (3) very natural conversational content, and possibly (4) insufficient training data. As an example of a dinner party scenario, we have chosen the data presented during the CHiME-5 speech recognition challenge, where the baseline ASR had a 73.3% word error rate (WER), and even the best performing system at the CHiME-5 challenge had a 46.1% WER. We extensively investigated a combination of the guided source separation-based speech enhancement technique and an already proposed strong ASR backend and found that a tight combination of these techniques provided substantial accuracy improvements. Our final system achieved WERs of 39.94% and 41.64% for the development and evaluation data, respectively, both of which are the best published results for the dataset. We also investigated with additional training data on the official small data in the CHiME-5 corpus to assess the intrinsic difficulty of this ASR task.

Shota Horiguchi, Sosuke Amano, Makoto Ogawa et al.

Currently, food image recognition tasks are evaluated against fixed datasets. However, in real-world conditions, there are cases in which the number of samples in each class continues to increase and samples from novel classes appear. In particular, dynamic datasets in which each individual user creates samples and continues the updating process often have content that varies considerably between different users, and the number of samples per person is very limited. A single classifier common to all users cannot handle such dynamic data. Bridging the gap between the laboratory environment and the real world has not yet been accomplished on a large scale. Personalizing a classifier incrementally for each user is a promising way to do this. In this paper, we address the personalization problem, which involves adapting to the user's domain incrementally using a very limited number of samples. We propose a simple yet effective personalization framework which is a combination of the nearest class mean classifier and the 1-nearest neighbor classifier based on deep features. To conduct realistic experiments, we made use of a new dataset of daily food images collected by a food-logging application. Experimental results show that our proposed method significantly outperforms existing methods.

Shota Horiguchi, Daiki Ikami, Kiyoharu Aizawa

The extraction of useful deep features is important for many computer vision tasks. Deep features extracted from classification networks have proved to perform well in those tasks. To obtain features of greater usefulness, end-to-end distance metric learning (DML) has been applied to train the feature extractor directly. However, in these DML studies, there were no equitable comparisons between features extracted from a DML-based network and those from a softmax-based network. In this paper, by presenting objective comparisons between these two approaches under the same network architecture, we show that the softmax-based features perform competitive, or even better, to the state-of-the-art DML features when the size of the dataset, that is, the number of training samples per class, is large. The results suggest that softmax-based features should be properly taken into account when evaluating the performance of deep features.