We propose an approach for cognitive coding of speech by unsupervised extraction of contextual representations in two hierarchical levels of abstraction. Speech attributes such as phoneme identity that last one hundred milliseconds or less are captured in the lower level of abstraction, while speech attributes such as speaker identity and emotion that persist up to one second are captured in the higher level of abstraction. This decomposition is achieved by a two-stage neural network, with a lower and an upper stage operating at different time scales. Both stages are trained to predict the content of the signal in their respective latent spaces. A top-down pathway between stages further improves the predictive capability of the network. With an application in speech compression in mind, we investigate the effect of dimensionality reduction and low bitrate quantization on the extracted representations. The performance measured on the LibriSpeech and EmoV-DB datasets reaches, and for some speech attributes even exceeds, that of state-of-the-art approaches.
相關內容
Audio-visual speaker diarization aims at detecting ``who spoken when`` using both auditory and visual signals. Existing audio-visual diarization datasets are mainly focused on indoor environments like meeting rooms or news studios, which are quite different from in-the-wild videos in many scenarios such as movies, documentaries, and audience sitcoms. To create a testbed that can effectively compare diarization methods on videos in the wild, we annotate the speaker diarization labels on the AVA movie dataset and create a new benchmark called AVA-AVD. This benchmark is challenging due to the diverse scenes, complicated acoustic conditions, and completely off-screen speakers. Yet, how to deal with off-screen and on-screen speakers together still remains a critical challenge. To overcome it, we propose a novel Audio-Visual Relation Network (AVR-Net) which introduces an effective modality mask to capture discriminative information based on visibility. Experiments have shown that our method not only can outperform state-of-the-art methods but also is more robust as varying the ratio of off-screen speakers. Ablation studies demonstrate the advantages of the proposed AVR-Net and especially the modality mask on diarization. Our data and code will be made publicly available at //github.com/zcxu-eric/AVA-AVD.
Deep Learning-based Non-Intrusive Multi-Objective Speech Assessment Model with Cross-Domain Features
In this study, we propose a cross-domain multi-objective speech assessment model called MOSA-Net, which can estimate multiple speech assessment metrics simultaneously. More specifically, MOSA-Net is designed to estimate the speech quality, intelligibility, and distortion assessment scores of an input test speech signal. It comprises a convolutional neural network and bidirectional long short-term memory (CNN-BLSTM) architecture for representation extraction, and a multiplicative attention layer and a fully-connected layer for each assessment metric. In addition, cross-domain features (spectral and time-domain features) and latent representations from self-supervised learned models are used as inputs to combine rich acoustic information from different speech representations to obtain more accurate assessments. Experimental results show that MOSA-Net can precisely predict perceptual evaluation of speech quality (PESQ), short-time objective intelligibility (STOI), and speech distortion index (SDI) scores when tested on noisy and enhanced speech utterances under either seen test conditions or unseen test conditions. Moreover, MOSA-Net, originally trained to assess objective scores, can be used as a pre-trained model to be effectively adapted to an assessment model for predicting subjective quality and intelligibility scores with a limited amount of training data. In light of the confirmed prediction capability, we further adopt the latent representations of MOSA-Net to guide the speech enhancement (SE) process and derive a quality-intelligibility (QI)-aware SE (QIA-SE) approach accordingly. Experimental results show that QIA-SE provides superior enhancement performance compared with the baseline SE system in terms of objective evaluation metrics and qualitative evaluation test.
One of the key communicative competencies is the ability to maintain fluency in monologic speech and the ability to produce sophisticated language to argue a position convincingly. In this paper we aim to predict TED talk-style affective ratings in a crowdsourced dataset of argumentative speech consisting of 7 hours of speech from 110 individuals. The speech samples were elicited through task prompts relating to three debating topics. The samples received a total of 2211 ratings from 737 human raters pertaining to 14 affective categories. We present an effective approach to the classification task of predicting these categories through fine-tuning a model pre-trained on a large dataset of TED talks public speeches. We use a combination of fluency features derived from a state-of-the-art automatic speech recognition system and a large set of human-interpretable linguistic features obtained from an automatic text analysis system. Classification accuracy was greater than 60% for all 14 rating categories, with a peak performance of 72% for the rating category 'informative'. In a secondary experiment, we determined the relative importance of features from different groups using SP-LIME.
Text to speech (TTS), or speech synthesis, which aims to synthesize intelligible and natural speech given text, is a hot research topic in speech, language, and machine learning communities and has broad applications in the industry. As the development of deep learning and artificial intelligence, neural network-based TTS has significantly improved the quality of synthesized speech in recent years. In this paper, we conduct a comprehensive survey on neural TTS, aiming to provide a good understanding of current research and future trends. We focus on the key components in neural TTS, including text analysis, acoustic models and vocoders, and several advanced topics, including fast TTS, low-resource TTS, robust TTS, expressive TTS, and adaptive TTS, etc. We further summarize resources related to TTS (e.g., datasets, opensource implementations) and discuss future research directions. This survey can serve both academic researchers and industry practitioners working on TTS.
Cognitive diagnosis is a fundamental issue in intelligent education, which aims to discover the proficiency level of students on specific knowledge concepts. Existing approaches usually mine linear interactions of student exercising process by manual-designed function (e.g., logistic function), which is not sufficient for capturing complex relations between students and exercises. In this paper, we propose a general Neural Cognitive Diagnosis (NeuralCD) framework, which incorporates neural networks to learn the complex exercising interactions, for getting both accurate and interpretable diagnosis results. Specifically, we project students and exercises to factor vectors and leverage multi neural layers for modeling their interactions, where the monotonicity assumption is applied to ensure the interpretability of both factors. Furthermore, we propose two implementations of NeuralCD by specializing the required concepts of each exercise, i.e., the NeuralCDM with traditional Q-matrix and the improved NeuralCDM+ exploring the rich text content. Extensive experimental results on real-world datasets show the effectiveness of NeuralCD framework with both accuracy and interpretability.
Recently, fully recurrent neural network (RNN) based end-to-end models have been proven to be effective for multi-speaker speech recognition in both the single-channel and multi-channel scenarios. In this work, we explore the use of Transformer models for these tasks by focusing on two aspects. First, we replace the RNN-based encoder-decoder in the speech recognition model with a Transformer architecture. Second, in order to use the Transformer in the masking network of the neural beamformer in the multi-channel case, we modify the self-attention component to be restricted to a segment rather than the whole sequence in order to reduce computation. Besides the model architecture improvements, we also incorporate an external dereverberation preprocessing, the weighted prediction error (WPE), enabling our model to handle reverberated signals. Experiments on the spatialized wsj1-2mix corpus show that the Transformer-based models achieve 40.9% and 25.6% relative WER reduction, down to 12.1% and 6.4% WER, under the anechoic condition in single-channel and multi-channel tasks, respectively, while in the reverberant case, our methods achieve 41.5% and 13.8% relative WER reduction, down to 16.5% and 15.2% WER.
The field of Text-to-Speech has experienced huge improvements last years benefiting from deep learning techniques. Producing realistic speech becomes possible now. As a consequence, the research on the control of the expressiveness, allowing to generate speech in different styles or manners, has attracted increasing attention lately. Systems able to control style have been developed and show impressive results. However the control parameters often consist of latent variables and remain complex to interpret. In this paper, we analyze and compare different latent spaces and obtain an interpretation of their influence on expressive speech. This will enable the possibility to build controllable speech synthesis systems with an understandable behaviour.
We present a meta-learning approach for adaptive text-to-speech (TTS) with few data. During training, we learn a multi-speaker model using a shared conditional WaveNet core and independent learned embeddings for each speaker. The aim of training is not to produce a neural network with fixed weights, which is then deployed as a TTS system. Instead, the aim is to produce a network that requires few data at deployment time to rapidly adapt to new speakers. We introduce and benchmark three strategies: (i) learning the speaker embedding while keeping the WaveNet core fixed, (ii) fine-tuning the entire architecture with stochastic gradient descent, and (iii) predicting the speaker embedding with a trained neural network encoder. The experiments show that these approaches are successful at adapting the multi-speaker neural network to new speakers, obtaining state-of-the-art results in both sample naturalness and voice similarity with merely a few minutes of audio data from new speakers.
We study the use of the Wave-U-Net architecture for speech enhancement, a model introduced by Stoller et al for the separation of music vocals and accompaniment. This end-to-end learning method for audio source separation operates directly in the time domain, permitting the integrated modelling of phase information and being able to take large temporal contexts into account. Our experiments show that the proposed method improves several metrics, namely PESQ, CSIG, CBAK, COVL and SSNR, over the state-of-the-art with respect to the speech enhancement task on the Voice Bank corpus (VCTK) dataset. We find that a reduced number of hidden layers is sufficient for speech enhancement in comparison to the original system designed for singing voice separation in music. We see this initial result as an encouraging signal to further explore speech enhancement in the time-domain, both as an end in itself and as a pre-processing step to speech recognition systems.
State-of-the-art speech recognition systems rely on fixed, hand-crafted features such as mel-filterbanks to preprocess the waveform before the training pipeline. In this paper, we study end-to-end systems trained directly from the raw waveform, building on two alternatives for trainable replacements of mel-filterbanks that use a convolutional architecture. The first one is inspired by gammatone filterbanks (Hoshen et al., 2015; Sainath et al, 2015), and the second one by the scattering transform (Zeghidour et al., 2017). We propose two modifications to these architectures and systematically compare them to mel-filterbanks, on the Wall Street Journal dataset. The first modification is the addition of an instance normalization layer, which greatly improves on the gammatone-based trainable filterbanks and speeds up the training of the scattering-based filterbanks. The second one relates to the low-pass filter used in these approaches. These modifications consistently improve performances for both approaches, and remove the need for a careful initialization in scattering-based trainable filterbanks. In particular, we show a consistent improvement in word error rate of the trainable filterbanks relatively to comparable mel-filterbanks. It is the first time end-to-end models trained from the raw signal significantly outperform mel-filterbanks on a large vocabulary task under clean recording conditions.
小貼士
登錄享
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191