In recent years, reinforcement learning and bandits have transformed a wide range of real-world applications including healthcare, finance, recommendation systems, robotics, and last but not least, the speech and natural language processing. While most speech and language applications of reinforcement learning algorithms are centered around improving the training of deep neural networks with its flexible optimization properties, there are still many grounds to explore to utilize the benefits of reinforcement learning, such as its reward-driven adaptability, state representations, temporal structures and generalizability. In this survey, we present an overview of recent advancements of reinforcement learning and bandits, and discuss how they can be effectively employed to solve speech and natural language processing problems with models that are adaptive, interactive and scalable.
Acoustic echo cancellation (AEC) is designed to remove echoes, reverberation, and unwanted added sounds from the microphone signal while maintaining the quality of the near-end speaker's speech. This paper proposes adaptive speech quality complex neural networks to focus on specific tasks for real-time acoustic echo cancellation. In specific, we propose a complex modularize neural network with different stages to focus on feature extraction, acoustic separation, and mask optimization receptively. Furthermore, we adopt the contrastive learning framework and novel speech quality aware loss functions to further improve the performance. The model is trained with 72 hours for pre-training and then 72 hours for fine-tuning. The proposed model outperforms the state-of-the-art performance.
Speech is the fundamental means of communication between humans. The advent of AI and sophisticated speech technologies have led to the rapid proliferation of human-to-computer-based interactions, fueled primarily by Automatic Speech Recognition (ASR) systems. ASR systems normally take human speech in the form of audio and convert it into words, but for some users, it cannot decode the speech, and any output text is filled with errors that are incomprehensible to the human reader. These systems do not work equally for everyone and actually hinder the productivity of some users. In this paper, we present research that addresses ASR biases against gender, race, and the sick and disabled, while exploring studies that propose ASR debiasing techniques for mitigating these discriminations. We also discuss techniques for designing a more accessible and inclusive ASR technology. For each approach surveyed, we also provide a summary of the investigation and methods applied, the ASR systems and corpora used, and the research findings, and highlight their strengths and/or weaknesses. Finally, we propose future opportunities for Natural Language Processing researchers to explore in the next level creation of ASR technologies.
Building automatic speech recognition (ASR) systems is a challenging task, especially for under-resourced languages that need to construct corpora nearly from scratch and lack sufficient training data. It has emerged that several African indigenous languages, including Kiswahili, are technologically under-resourced. ASR systems are crucial, particularly for the hearing-impaired persons who can benefit from having transcripts in their native languages. However, the absence of transcribed speech datasets has complicated efforts to develop ASR models for these indigenous languages. This paper explores the transcription process and the development of a Kiswahili speech corpus, which includes both read-out texts and spontaneous speech data from native Kiswahili speakers. The study also discusses the vowels and consonants in Kiswahili and provides an updated Kiswahili phoneme dictionary for the ASR model that was created using the CMU Sphinx speech recognition toolbox, an open-source speech recognition toolkit. The ASR model was trained using an extended phonetic set that yielded a WER and SER of 18.87% and 49.5%, respectively, an improved performance than previous similar research for under-resourced languages.
Recently studies on time-domain audio separation networks (TasNets) have made a great stride in speech separation. One of the most representative TasNets is a network with a dual-path segmentation approach. However, the original model called DPRNN used a fixed feature dimension and unchanged segment size throughout all layers of the network. In this paper, we propose a multi-scale feature fusion transformer network (MSFFT-Net) based on the conventional dual-path structure for single-channel speech separation. Unlike the conventional dual-path structure where only one processing path exists, adopting several iterative blocks with alternative intra-chunk and inter-chunk operations to capture local and global context information, the proposed MSFFT-Net has multiple parallel processing paths where the feature information can be exchanged between multiple parallel processing paths. Experiments show that our proposed networks based on multi-scale feature fusion structure have achieved better results than the original dual-path model on the benchmark dataset-WSJ0-2mix, where the SI-SNRi score of MSFFT-3P is 20.7dB (1.47% improvement), and MSFFT-2P is 21.0dB (3.45% improvement), which achieves SOTA on WSJ0-2mix without any data augmentation method.
Automatic synthesis of realistic co-speech gestures is an increasingly important yet challenging task in artificial embodied agent creation. Previous systems mainly focus on generating gestures in an end-to-end manner, which leads to difficulties in mining the clear rhythm and semantics due to the complex yet subtle harmony between speech and gestures. We present a novel co-speech gesture synthesis method that achieves convincing results both on the rhythm and semantics. For the rhythm, our system contains a robust rhythm-based segmentation pipeline to ensure the temporal coherence between the vocalization and gestures explicitly. For the gesture semantics, we devise a mechanism to effectively disentangle both low- and high-level neural embeddings of speech and motion based on linguistic theory. The high-level embedding corresponds to semantics, while the low-level embedding relates to subtle variations. Lastly, we build correspondence between the hierarchical embeddings of the speech and the motion, resulting in rhythm- and semantics-aware gesture synthesis. Evaluations with existing objective metrics, a newly proposed rhythmic metric, and human feedback show that our method outperforms state-of-the-art systems by a clear margin.
Deep learning based text-to-speech (TTS) systems have been evolving rapidly with advances in model architectures, training methodologies, and generalization across speakers and languages. However, these advances have not been thoroughly investigated for Indian language speech synthesis. Such investigation is computationally expensive given the number and diversity of Indian languages, relatively lower resource availability, and the diverse set of advances in neural TTS that remain untested. In this paper, we evaluate the choice of acoustic models, vocoders, supplementary loss functions, training schedules, and speaker and language diversity for Dravidian and Indo-Aryan languages. Based on this, we identify monolingual models with FastPitch and HiFi-GAN V1, trained jointly on male and female speakers to perform the best. With this setup, we train and evaluate TTS models for 13 languages and find our models to significantly improve upon existing models in all languages as measured by mean opinion scores. We open-source all models on the Bhashini platform.
Recent studies of streaming automatic speech recognition (ASR) recurrent neural network transducer (RNN-T)-based systems have fed the encoder with past contextual information in order to improve its word error rate (WER) performance. In this paper, we first propose a contextual-utterance training technique which makes use of the previous and future contextual utterances in order to do an implicit adaptation to the speaker, topic and acoustic environment. Also, we propose a dual-mode contextual-utterance training technique for streaming automatic speech recognition (ASR) systems. This proposed approach allows to make a better use of the available acoustic context in streaming models by distilling "in-place" the knowledge of a teacher, which is able to see both past and future contextual utterances, to the student which can only see the current and past contextual utterances. The experimental results show that a conformer-transducer system trained with the proposed techniques outperforms the same system trained with the classical RNN-T loss. Specifically, the proposed technique is able to reduce both the WER and the average last token emission latency by more than 6% and 40ms relative, respectively.
Many self-supervised speech models, varying in their pre-training objective, input modality, and pre-training data, have been proposed in the last few years. Despite impressive empirical successes on downstream tasks, we still have a limited understanding of the properties encoded by the models and the differences across models. In this work, we examine the intermediate representations for a variety of recent models. Specifically, we measure acoustic, phonetic, and word-level properties encoded in individual layers, using a lightweight analysis tool based on canonical correlation analysis (CCA). We find that these properties evolve across layers differently depending on the model, and the variations relate to the choice of pre-training objective. We further investigate the utility of our analyses for downstream tasks by comparing the property trends with performance on speech recognition and spoken language understanding tasks. We discover that CCA trends provide reliable guidance to choose layers of interest for downstream tasks and that single-layer performance often matches or improves upon using all layers, suggesting implications for more efficient use of pre-trained models.
We present a unified system to realize one-shot voice conversion (VC) on the pitch, rhythm, and speaker attributes. Existing works generally ignore the correlation between prosody and language content, leading to the degradation of naturalness in converted speech. Additionally, the lack of proper language features prevents these systems from accurately preserving language content after conversion. To address these issues, we devise a cascaded modular system leveraging self-supervised discrete speech units as language representation. These discrete units provide duration information essential for rhythm modeling. Our system first extracts utterance-level prosody and speaker representations from the raw waveform. Given the prosody representation, a prosody predictor estimates pitch, energy, and duration for each discrete unit in the utterance. A synthesizer further reconstructs speech based on the predicted prosody, speaker representation, and discrete units. Experiments show that our system outperforms previous approaches in naturalness, intelligibility, speaker transferability, and prosody transferability. Code and samples are publicly available.