Non-autoregressive mechanisms can significantly decrease inference time for speech transformers, especially when the single step variant is applied. Previous work on CTC alignment-based single step non-autoregressive transformer (CASS-NAT) has shown a large real time factor (RTF) improvement over autoregressive transformers (AT). In this work, we propose several methods to improve the accuracy of the end-to-end CASS-NAT, followed by performance analyses. First, convolution augmented self-attention blocks are applied to both the encoder and decoder modules. Second, we propose to expand the trigger mask (acoustic boundary) for each token to increase the robustness of CTC alignments. In addition, iterated loss functions are used to enhance the gradient update of low-layer parameters. Without using an external language model, the WERs of the improved CASS-NAT, when using the three methods, are 3.1%/7.2% on Librispeech test clean/other sets and the CER is 5.4% on the Aishell1 test set, achieving a 7%~21% relative WER/CER improvement. For the analyses, we plot attention weight distributions in the decoders to visualize the relationships between token-level acoustic embeddings. When the acoustic embeddings are visualized, we find that they have a similar behavior to word embeddings, which explains why the improved CASS-NAT performs similarly to AT.
Rank-constrained spatial covariance matrix estimation (RCSCME) is a state-of-the-art blind speech extraction method applied to cases where one directional target speech and diffuse noise are mixed. In this paper, we proposed a new algorithmic extension of RCSCME. RCSCME complements a deficient one rank of the diffuse noise spatial covariance matrix, which cannot be estimated via preprocessing such as independent low-rank matrix analysis, and estimates the source model parameters simultaneously. In the conventional RCSCME, a direction of the deficient basis is fixed in advance and only the scale is estimated; however, the candidate of this deficient basis is not unique in general. In the proposed RCSCME model, the deficient basis itself can be accurately estimated as a vector variable by solving a vector optimization problem. Also, we derive new update rules based on the EM algorithm. We confirm that the proposed method outperforms conventional methods under several noise conditions.
In this work, we conduct an extensive comparison of various approaches to speech based emotion recognition systems. The analyses were carried out on audio recordings from Ryerson Audio-Visual Database of Emotional Speech and Song (RAVDESS). After pre-processing the raw audio files, features such as Log-Mel Spectrogram, Mel-Frequency Cepstral Coefficients (MFCCs), pitch and energy were considered. The significance of these features for emotion classification was compared by applying methods such as Long Short Term Memory (LSTM), Convolutional Neural Networks (CNNs), Hidden Markov Models (HMMs) and Deep Neural Networks (DNNs). On the 14-class (2 genders x 7 emotions) classification task, an accuracy of 68% was achieved with a 4-layer 2 dimensional CNN using the Log-Mel Spectrogram features. We also observe that, in emotion recognition, the choice of audio features impacts the results much more than the model complexity.
Target speech extraction, which extracts a single target source in a mixture given clues about the target speaker, has attracted increasing attention. We have recently proposed SpeakerBeam, which exploits an adaptation utterance of the target speaker to extract his/her voice characteristics that are then used to guide a neural network towards extracting speech of that speaker. SpeakerBeam presents a practical alternative to speech separation as it enables tracking speech of a target speaker across utterances, and achieves promising speech extraction performance. However, it sometimes fails when speakers have similar voice characteristics, such as in same-gender mixtures, because it is difficult to discriminate the target speaker from the interfering speakers. In this paper, we investigate strategies for improving the speaker discrimination capability of SpeakerBeam. First, we propose a time-domain implementation of SpeakerBeam similar to that proposed for a time-domain audio separation network (TasNet), which has achieved state-of-the-art performance for speech separation. Besides, we investigate (1) the use of spatial features to better discriminate speakers when microphone array recordings are available, (2) adding an auxiliary speaker identification loss for helping to learn more discriminative voice characteristics. We show experimentally that these strategies greatly improve speech extraction performance, especially for same-gender mixtures, and outperform TasNet in terms of target speech extraction.
Voice conversion (VC) has been proposed to improve speech recognition systems in low-resource languages by using it to augment limited training data. But until recently, practical issues such as compute speed have limited the use of VC for this purpose. Moreover, it is still unclear whether a VC model trained on one well-resourced language can be applied to speech from another low-resource language for the purpose of data augmentation. In this work we assess whether a VC system can be used cross-lingually to improve low-resource speech recognition. Concretely, we combine several recent techniques to design and train a practical VC system in English, and then use this system to augment data for training a speech recognition model in several low-resource languages. We find that when using a sensible amount of augmented data, speech recognition performance is improved in all four low-resource languages considered.
Attention-based sequence-to-sequence (seq2seq) speech synthesis has achieved extraordinary performance. But a studio-quality corpus with manual transcription is necessary to train such seq2seq systems. In this paper, we propose an approach to build high-quality and stable seq2seq based speech synthesis system using challenging found data, where training speech contains noisy interferences (acoustic noise) and texts are imperfect speech recognition transcripts (textual noise). To deal with text-side noise, we propose a VQVAE based heuristic method to compensate erroneous linguistic feature with phonetic information learned directly from speech. As for the speech-side noise, we propose to learn a noise-independent feature in the auto-regressive decoder through adversarial training and data augmentation, which does not need an extra speech enhancement model. Experiments show the effectiveness of the proposed approach in dealing with text-side and speech-side noise. Surpassing the denoising approach based on a state-of-the-art speech enhancement model, our system built on noisy found data can synthesize clean and high-quality speech with MOS close to the system built on the clean counterpart.
Current research on hate speech analysis is typically oriented towards monolingual and single classification tasks. In this paper, we present a new multilingual multi-aspect hate speech analysis dataset and use it to test the current state-of-the-art multilingual multitask learning approaches. We evaluate our dataset in various classification settings, then we discuss how to leverage our annotations in order to improve hate speech detection and classification in general.
Emotion recognition from audio signals has been regarded as a challenging task in signal processing as it can be considered as a collection of static and dynamic classification tasks. Recognition of emotions from speech data has been heavily relied upon end-to-end feature extraction and classification using machine learning models, though the absence of feature selection and optimization have restrained the performance of these methods. Recent studies have shown that Mel Frequency Cepstral Coefficients (MFCC) have been emerged as one of the most relied feature extraction methods, though it circumscribes the accuracy of classification with a very small feature dimension. In this paper, we propose that the concatenation of features, extracted by using different existing feature extraction methods can not only boost the classification accuracy but also expands the possibility of efficient feature selection. We have used Linear Predictive Coding (LPC) apart from the MFCC feature extraction method, before feature merging. Besides, we have performed a novel application of Manta Ray optimization in speech emotion recognition tasks that resulted in a state-of-the-art result in this field. We have evaluated the performance of our model using SAVEE and Emo-DB, two publicly available datasets. Our proposed method outperformed all the existing methods in speech emotion analysis and resulted in a decent result in these two datasets with a classification accuracy of 97.06% and 97.68% respectively.
Neural network applications generally benefit from larger-sized models, but for current speech enhancement models, larger scale networks often suffer from decreased robustness to the variety of real-world use cases beyond what is encountered in training data. We introduce several innovations that lead to better large neural networks for speech enhancement. The novel PoCoNet architecture is a convolutional neural network that, with the use of frequency-positional embeddings, is able to more efficiently build frequency-dependent features in the early layers. A semi-supervised method helps increase the amount of conversational training data by pre-enhancing noisy datasets, improving performance on real recordings. A new loss function biased towards preserving speech quality helps the optimization better match human perceptual opinions on speech quality. Ablation experiments and objective and human opinion metrics show the benefits of the proposed improvements.
Automatic speech recognition systems have been largely improved in the past few decades and current systems are mainly hybrid-based and end-to-end-based. The recently proposed CTC-CRF framework inherits the data-efficiency of the hybrid approach and the simplicity of the end-to-end approach. In this paper, we further advance CTC-CRF based ASR technique with explorations on modeling units and neural architectures. Specifically, we investigate techniques to enable the recently developed wordpiece modeling units and Conformer neural networks to be succesfully applied in CTC-CRFs. Experiments are conducted on two English datasets (Switchboard, Librispeech) and a German dataset from CommonVoice. Experimental results suggest that (i) Conformer can improve the recognition performance significantly; (ii) Wordpiece-based systems perform slightly worse compared with phone-based systems for the target language with a low degree of grapheme-phoneme correspondence (e.g. English), while the two systems can perform equally strong when such degree of correspondence is high for the target language (e.g. German).