Hiroshi Sato

Atsushi Ando, Ryo Masumura, Akihiko Takashima et al.

This paper investigates the effectiveness and implementation of modality-specific large-scale pre-trained encoders for multimodal sentiment analysis~(MSA). Although the effectiveness of pre-trained encoders in various fields has been reported, conventional MSA methods employ them for only linguistic modality, and their application has not been investigated. This paper compares the features yielded by large-scale pre-trained encoders with conventional heuristic features. One each of the largest pre-trained encoders publicly available for each modality are used; CLIP-ViT, WavLM, and BERT for visual, acoustic, and linguistic modalities, respectively. Experiments on two datasets reveal that methods with domain-specific pre-trained encoders attain better performance than those with conventional features in both unimodal and multimodal scenarios. We also find it better to use the outputs of the intermediate layers of the encoders than those of the output layer. The codes are available at https://github.com/ando-hub/MSA_Pretrain.

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.

Daisuke Yasui, Toshitaka Matuki, Hiroshi Sato

Deep reinforcement learning (DRL) has been shown to achieve high performance on locomotion control tasks in MuJoCo benchmarks such as HalfCheetah, Ant, and Walker2D. However, visualizing the motion structures internally obtained by a trained policy function implemented as a deep neural network remains challenging. It is known from biomechanics and related fields that locomotion control is realized through the repetition of motion phases such as the stance phase and swing phase. In this study, we propose a framework for uncovering latent motion phase structures from trajectories generated by locomotion control policies through interaction with the environment. The proposed method extends the clustering features from state observations alone to augmented features including actions, next states, and next actions, and introduces a method for determining the number of clusters that suppresses self-transitions. Applying the proposed method to three environments -- Ant-v5, HalfCheetah-v5, and Walker2D-v5 -- we successfully identified phase structures with clearer and more regular transition rules than those obtained by the existing method.

Ryo Masumura, Naoki Makishima, Taiga Yamane et al.

This paper proposes a novel automatic speech recognition (ASR) system that can transcribe individual speaker's speech while identifying whether they are target or non-target speakers from multi-talker overlapped speech. Target-speaker ASR systems are a promising way to only transcribe a target speaker's speech by enrolling the target speaker's information. However, in conversational ASR applications, transcribing both the target speaker's speech and non-target speakers' ones is often required to understand interactive information. To naturally consider both target and non-target speakers in a single ASR model, our idea is to extend autoregressive modeling-based multi-talker ASR systems to utilize the enrollment speech of the target speaker. Our proposed ASR is performed by recursively generating both textual tokens and tokens that represent target or non-target speakers. Our experiments demonstrate the effectiveness of our proposed method.

Takafumi Moriya, Takanori Ashihara, Masato Mimura et al.

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 internal acoustic model (IAM) training strategy to enhance HAT-based speech recognition. IAM consists of encoder and joint networks, which are fully shared and jointly trained with HAT. This joint training not only enhances the HAT training efficiency but also encourages IAM and HAT to emit blanks synchronously which skips the more expensive non-blank computation, resulting in more effective blank thresholding for faster decoding. Experiments demonstrate that the relative error reductions of the HAT with IAM compared to the vanilla HAT are statistically significant. Moreover, we introduce dual blank thresholding, which combines both HAT- and IAM-blank thresholding and a compatible decoding algorithm. This results in a 42-75% decoding speed-up with no major performance degradation.

Daisuke Yasui, Toshitaka Matsuki, Hiroshi Sato

In locomotion control tasks, Deep Reinforcement Learning (DRL) has demonstrated high performance; however, the decision-making process of the learned policy remains a black box, making it difficult for humans to understand. On the other hand, in periodic motions such as walking, it is well known that implicit motion phases exist, such as the stance phase and the swing phase. Focusing on this point, this study hypothesizes that a policy trained for locomotion control may also represent a phase structure that is interpretable by humans. To examine this hypothesis in a controlled setting, we consider a locomotion task that is amenable to observing whether a policy autonomously acquires temporally structured phases through interaction with the environment. To verify this hypothesis, in the MuJoCo locomotion benchmark HalfCheetah-v5, the state transition sequences acquired by a policy trained for walking control through interaction with the environment were aggregated into semantic phases based on state similarity and consistency of subsequent transitions. As a result, we demonstrated that the state sequences generated by the trained policy exhibit periodic phase transition structures as well as phase branching. Furthermore, by approximating the states and actions corresponding to each semantic phase using Explainable Boosting Machines (EBMs), we analyzed phase-dependent decision making-namely, which state features the policy function attends to and how it controls action outputs in each phase. These results suggest that neural network-based policies, which are often regarded as black boxes, can autonomously acquire interpretable phase structures and logical branching mechanisms.

Daisuke Yasui, Toshitaka Matsuki, Hiroshi Sato

Convolutional Neural Networks (CNNs) are widely used in image recognition and have succeeded in various domains. CNN models have become larger-scale to improve accuracy and generalization performance. Research has been conducted on compressing pre-trained models for specific target applications in environments with limited computing resources. Among model compression techniques, methods using Layer-wise Relevance Propagation (LRP), an explainable AI technique, have shown promise by achieving high pruning rates while preserving accuracy, even without fine-tuning. Because these methods do not require fine-tuning, they are suited to scenarios with limited data. However, existing LRP-based pruning approaches still suffer from significant accuracy degradation, limiting their practical usability. This study proposes a pruning method that achieves a higher pruning rate while preserving better model accuracy. Our approach to pruning with a small amount of data has achieved pruning that preserves accuracy better than existing methods.

Kenichi Fujita, Hiroshi Sato, Takanori Ashihara et al.

The zero-shot text-to-speech (TTS) method, based on speaker embeddings extracted from reference speech using self-supervised learning (SSL) speech representations, can reproduce speaker characteristics very accurately. However, this approach suffers from degradation in speech synthesis quality when the reference speech contains noise. In this paper, we propose a noise-robust zero-shot TTS method. We incorporated adapters into the SSL model, which we fine-tuned with the TTS model using noisy reference speech. In addition, to further improve performance, we adopted a speech enhancement (SE) front-end. With these improvements, our proposed SSL-based zero-shot TTS achieved high-quality speech synthesis with noisy reference speech. Through the objective and subjective evaluations, we confirmed that the proposed method is highly robust to noise in reference speech, and effectively works in combination with SE.

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.

Nozomu Masuya, Hiroshi Sato, Koki Yamane et al.

Because imitation learning relies on human demonstrations in hard-to-simulate settings, the inclusion of force control in this method has resulted in a shortage of training data, even with a simple change in speed. Although the field of data augmentation has addressed the lack of data, conventional methods of data augmentation for robot manipulation are limited to simulation-based methods or downsampling for position control. This paper proposes a novel method of data augmentation that is applicable to force control and preserves the advantages of real-world datasets. We applied teaching-playback at variable speeds as real-world data augmentation to increase both the quantity and quality of environmental reactions at variable speeds. An experiment was conducted on bilateral control-based imitation learning using a method of imitation learning equipped with position-force control. We evaluated the effect of real-world data augmentation on two tasks, pick-and-place and wiping, at variable speeds, each from two human demonstrations at fixed speed. The results showed a maximum 55% increase in success rate from a simple change in speed of real-world reactions and improved accuracy along the duration/frequency command by gathering environmental reactions at variable speeds.

Hiroshi Sato, Masashi Konosu, Sho Sakaino et al.

In recent years, imitation learning using neural networks has enabled robots to perform flexible tasks. However, since neural networks operate in a feedforward structure, they do not possess a mechanism to compensate for output errors. To address this limitation, we developed a feedback mechanism to correct these errors. By employing a hierarchical structure for neural networks comprising lower and upper layers, the lower layer was controlled to follow the upper layer. Additionally, using a multi-layer perceptron in the lower layer, which lacks an internal state, enhanced the error feedback. In the character-writing task, this model demonstrated improved accuracy in writing previously untrained characters. In the character-writing task, this model demonstrated improved accuracy in writing previously untrained characters. Through autonomous control with error feedback, we confirmed that the lower layer could effectively track the output of the upper layer. This study represents a promising step toward integrating neural networks with control theories.

Kazuma Iwamoto, Tsubasa Ochiai, Marc Delcroix et al.

It is challenging to improve automatic speech recognition (ASR) performance in noisy conditions with single-channel speech enhancement (SE). In this paper, we investigate the causes of ASR performance degradation by decomposing the SE errors using orthogonal projection-based decomposition (OPD). OPD decomposes the SE errors into noise and artifact components. The artifact component is defined as the SE error signal that cannot be represented as a linear combination of speech and noise sources. We propose manually scaling the error components to analyze their impact on ASR. We experimentally identify the artifact component as the main cause of performance degradation, and we find that mitigating the artifact can greatly improve ASR performance. Furthermore, we demonstrate that the simple observation adding (OA) technique (i.e., adding a scaled version of the observed signal to the enhanced speech) can monotonically increase the signal-to-artifact ratio under a mild condition. Accordingly, we experimentally confirm that OA improves ASR performance for both simulated and real recordings. The findings of this paper provide a better understanding of the influence of SE errors on ASR and open the door to future research on novel approaches for designing effective single-channel SE front-ends for ASR.

Hiroshi Sato, Tsubasa Ochiai, Marc Delcroix et al.

The combination of a deep neural network (DNN) -based speech enhancement (SE) front-end and an automatic speech recognition (ASR) back-end is a widely used approach to implement overlapping speech recognition. However, the SE front-end generates processing artifacts that can degrade the ASR performance. We previously found that such performance degradation can occur even under fully overlapping conditions, depending on the signal-to-interference ratio (SIR) and signal-to-noise ratio (SNR). To mitigate the degradation, we introduced a rule-based method to switch the ASR input between the enhanced and observed signals, which showed promising results. However, the rule's optimality was unclear because it was heuristically designed and based only on SIR and SNR values. In this work, we propose a DNN-based switching method that directly estimates whether ASR will perform better on the enhanced or observed signals. We also introduce soft-switching that computes a weighted sum of the enhanced and observed signals for ASR input, with weights given by the switching model's output posteriors. The proposed learning-based switching showed performance comparable to that of rule-based oracle switching. The soft-switching further improved the ASR performance and achieved a relative character error rate reduction of up to 23 % as compared with the conventional method.

Hiroshi Sato, Tsubasa Ochiai, Marc Delcroix et al.

Although recent advances in deep learning technology improved automatic speech recognition (ASR), it remains difficult to recognize speech when it overlaps other people's voices. Speech separation or extraction is often used as a front-end to ASR to handle such overlapping speech. However, deep neural network-based speech enhancement can generate `processing artifacts' as a side effect of the enhancement, which degrades ASR performance. For example, it is well known that single-channel noise reduction for non-speech noise (non-overlapping speech) often does not improve ASR. Likewise, the processing artifacts may also be detrimental to ASR in some conditions when processing overlapping speech with a separation/extraction method, although it is usually believed that separation/extraction improves ASR. In order to answer the question `Do we always have to separate/extract speech from mixtures?', we analyze ASR performance on observed and enhanced speech at various noise and interference conditions, and show that speech enhancement degrades ASR under some conditions even for overlapping speech. Based on these findings, we propose a simple switching algorithm between observed and enhanced speech based on the estimated signal-to-interference ratio and signal-to-noise ratio. We demonstrated experimentally that such a simple switching mechanism can improve recognition performance when processing artifacts are detrimental to ASR.

Hiroshi Sato, Tsubasa Ochiai, Keisuke Kinoshita et al.

Target speaker extraction, which aims at extracting a target speaker's voice from a mixture of voices using audio, visual or locational clues, has received much interest. Recently an audio-visual target speaker extraction has been proposed that extracts target speech by using complementary audio and visual clues. Although audio-visual target speaker extraction offers a more stable performance than single modality methods for simulated data, its adaptation towards realistic situations has not been fully explored as well as evaluations on real recorded mixtures. One of the major issues to handle realistic situations is how to make the system robust to clue corruption because in real recordings both clues may not be equally reliable, e.g. visual clues may be affected by occlusions. In this work, we propose a novel attention mechanism for multi-modal fusion and its training methods that enable to effectively capture the reliability of the clues and weight the more reliable ones. Our proposals improve signal to distortion ratio (SDR) by 1.0 dB over conventional fusion mechanisms on simulated data. Moreover, we also record an audio-visual dataset of simultaneous speech with realistic visual clue corruption and show that audio-visual target speaker extraction with our proposals successfully work on real data.