Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

"speech": models, code, and papers

Enhancing into the codec: Noise Robust Speech Coding with Vector-Quantized Autoencoders

Feb 12, 2021
Jonah Casebeer, Vinjai Vale, Umut Isik, Jean-Marc Valin, Ritwik Giri, Arvindh Krishnaswamy

Audio codecs based on discretized neural autoencoders have recently been developed and shown to provide significantly higher compression levels for comparable quality speech output. However, these models are tightly coupled with speech content, and produce unintended outputs in noisy conditions. Based on VQ-VAE autoencoders with WaveRNN decoders, we develop compressor-enhancer encoders and accompanying decoders, and show that they operate well in noisy conditions. We also observe that a compressor-enhancer model performs better on clean speech inputs than a compressor model trained only on clean speech.

* 5 pages, 2 figures, ICASSP 2021 

  Access Paper or Ask Questions

State-of-the-Art Speech Recognition Using Multi-Stream Self-Attention With Dilated 1D Convolutions

Oct 01, 2019
Kyu J. Han, Ramon Prieto, Kaixing Wu, Tao Ma

Self-attention has been a huge success for many downstream tasks in NLP, which led to exploration of applying self-attention to speech problems as well. The efficacy of self-attention in speech applications, however, seems not fully blown yet since it is challenging to handle highly correlated speech frames in the context of self-attention. In this paper we propose a new neural network model architecture, namely multi-stream self-attention, to address the issue thus make the self-attention mechanism more effective for speech recognition. The proposed model architecture consists of parallel streams of self-attention encoders, and each stream has layers of 1D convolutions with dilated kernels whose dilation rates are unique given stream, followed by a self-attention layer. The self-attention mechanism in each stream pays attention to only one resolution of input speech frames and the attentive computation can be more efficient. In a later stage, outputs from all the streams are concatenated then linearly projected to the final embedding. By stacking the proposed multi-stream self-attention encoder blocks and rescoring the resultant lattices with neural network language models, we achieve the word error rate of 2.2% on the test-clean dataset of the LibriSpeech corpus, the best number reported thus far on the dataset.

* Accepted to ASRU 2019 

  Access Paper or Ask Questions

Hate Speech Detection in Clubhouse

Jul 11, 2021
Hadi Mansourifar, Dana Alsagheer, Reza Fathi, Weidong Shi, Lan Ni, Yan Huang

With the rise of voice chat rooms, a gigantic resource of data can be exposed to the research community for natural language processing tasks. Moderators in voice chat rooms actively monitor the discussions and remove the participants with offensive language. However, it makes the hate speech detection even more difficult since some participants try to find creative ways to articulate hate speech. This makes the hate speech detection challenging in new social media like Clubhouse. To the best of our knowledge all the hate speech datasets have been collected from text resources like Twitter. In this paper, we take the first step to collect a significant dataset from Clubhouse as the rising star in social media industry. We analyze the collected instances from statistical point of view using the Google Perspective Scores. Our experiments show that, the Perspective Scores can outperform Bag of Words and Word2Vec as high level text features.

  Access Paper or Ask Questions

Talking Head Generation Driven by Speech-Related Facial Action Units and Audio- Based on Multimodal Representation Fusion

Apr 27, 2022
Sen Chen, Zhilei Liu, Jiaxing Liu, Longbiao Wang

Talking head generation is to synthesize a lip-synchronized talking head video by inputting an arbitrary face image and corresponding audio clips. Existing methods ignore not only the interaction and relationship of cross-modal information, but also the local driving information of the mouth muscles. In this study, we propose a novel generative framework that contains a dilated non-causal temporal convolutional self-attention network as a multimodal fusion module to promote the relationship learning of cross-modal features. In addition, our proposed method uses both audio- and speech-related facial action units (AUs) as driving information. Speech-related AU information can guide mouth movements more accurately. Because speech is highly correlated with speech-related AUs, we propose an audio-to-AU module to predict speech-related AU information. We utilize pre-trained AU classifier to ensure that the generated images contain correct AU information. We verify the effectiveness of the proposed model on the GRID and TCD-TIMIT datasets. An ablation study is also conducted to verify the contribution of each component. The results of quantitative and qualitative experiments demonstrate that our method outperforms existing methods in terms of both image quality and lip-sync accuracy.

* arXiv admin note: text overlap with arXiv:2110.09951 

  Access Paper or Ask Questions

A Convolutional Neural Network model based on Neutrosophy for Noisy Speech Recognition

Jan 27, 2019
Elyas Rashno, Ahmad Akbari, Babak Nasersharif

Convolutional neural networks are sensitive to unknown noisy condition in the test phase and so their performance degrades for the noisy data classification task including noisy speech recognition. In this research, a new convolutional neural network (CNN) model with data uncertainty handling; referred as NCNN (Neutrosophic Convolutional Neural Network); is proposed for classification task. Here, speech signals are used as input data and their noise is modeled as uncertainty. In this task, using speech spectrogram, a definition of uncertainty is proposed in neutrosophic (NS) domain. Uncertainty is computed for each Time-frequency point of speech spectrogram as like a pixel. Therefore, uncertainty matrix with the same size of spectrogram is created in NS domain. In the next step, a two parallel paths CNN classification model is proposed. Speech spectrogram is used as input of the first path and uncertainty matrix for the second path. The outputs of two paths are combined to compute the final output of the classifier. To show the effectiveness of the proposed method, it has been compared with conventional CNN on the isolated words of Aurora2 dataset. The proposed method achieves the average accuracy of 85.96 in noisy train data. It is more robust against Car, Airport and Subway noises with accuracies 90, 88 and 81 in test sets A, B and C, respectively. Results show that the proposed method outperforms conventional CNN with the improvement of 6, 5 and 2 percentage in test set A, test set B and test sets C, respectively. It means that the proposed method is more robust against noisy data and handle these data effectively.

* Accepted on International conference on Pattern Recognition and Image Analysis (IPRIA), 6 pages 

  Access Paper or Ask Questions

Algorithms for Speech Recognition and Language Processing

Sep 17, 1996
Mehryar Mohri, Michael Riley, Richard Sproat

Speech processing requires very efficient methods and algorithms. Finite-state transducers have been shown recently both to constitute a very useful abstract model and to lead to highly efficient time and space algorithms in this field. We present these methods and algorithms and illustrate them in the case of speech recognition. In addition to classical techniques, we describe many new algorithms such as minimization, global and local on-the-fly determinization of weighted automata, and efficient composition of transducers. These methods are currently used in large vocabulary speech recognition systems. We then show how the same formalism and algorithms can be used in text-to-speech applications and related areas of language processing such as morphology, syntax, and local grammars, in a very efficient way. The tutorial is self-contained and requires no specific computational or linguistic knowledge other than classical results.

* Postscript file tar-compressed and uuencoded, 189 pages 

  Access Paper or Ask Questions

Anti-Asian Hate Speech Detection via Data Augmented Semantic Relation Inference

Apr 14, 2022
Jiaxuan Li, Yue Ning

With the spreading of hate speech on social media in recent years, automatic detection of hate speech is becoming a crucial task and has attracted attention from various communities. This task aims to recognize online posts (e.g., tweets) that contain hateful information. The peculiarities of languages in social media, such as short and poorly written content, lead to the difficulty of learning semantics and capturing discriminative features of hate speech. Previous studies have utilized additional useful resources, such as sentiment hashtags, to improve the performance of hate speech detection. Hashtags are added as input features serving either as sentiment-lexicons or extra context information. However, our close investigation shows that directly leveraging these features without considering their context may introduce noise to classifiers. In this paper, we propose a novel approach to leverage sentiment hashtags to enhance hate speech detection in a natural language inference framework. We design a novel framework SRIC that simultaneously performs two tasks: (1) semantic relation inference between online posts and sentiment hashtags, and (2) sentiment classification on these posts. The semantic relation inference aims to encourage the model to encode sentiment-indicative information into representations of online posts. We conduct extensive experiments on two real-world datasets and demonstrate the effectiveness of our proposed framework compared with state-of-the-art representation learning models.

* To appear in Proceedings of the 16th International AAAI Conference on Web and Social Media (ICWSM) 

  Access Paper or Ask Questions

Unsupervised Speech Representation Learning for Behavior Modeling using Triplet Enhanced Contextualized Networks

Apr 01, 2021
Haoqi Li, Brian Baucom, Shrikanth Narayanan, Panayiotis Georgiou

Speech encodes a wealth of information related to human behavior and has been used in a variety of automated behavior recognition tasks. However, extracting behavioral information from speech remains challenging including due to inadequate training data resources stemming from the often low occurrence frequencies of specific behavioral patterns. Moreover, supervised behavioral modeling typically relies on domain-specific construct definitions and corresponding manually-annotated data, rendering generalizing across domains challenging. In this paper, we exploit the stationary properties of human behavior within an interaction and present a representation learning method to capture behavioral information from speech in an unsupervised way. We hypothesize that nearby segments of speech share the same behavioral context and hence map onto similar underlying behavioral representations. We present an encoder-decoder based Deep Contextualized Network (DCN) as well as a Triplet-Enhanced DCN (TE-DCN) framework to capture the behavioral context and derive a manifold representation, where speech frames with similar behaviors are closer while frames of different behaviors maintain larger distances. The models are trained on movie audio data and validated on diverse domains including on a couples therapy corpus and other publicly collected data (e.g., stand-up comedy). With encouraging results, our proposed framework shows the feasibility of unsupervised learning within cross-domain behavioral modeling.

  Access Paper or Ask Questions

Few-shot Learning in Emotion Recognition of Spontaneous Speech Using a Siamese Neural Network with Adaptive Sample Pair Formation

Sep 07, 2021
Kexin Feng, Theodora Chaspari

Speech-based machine learning (ML) has been heralded as a promising solution for tracking prosodic and spectrotemporal patterns in real-life that are indicative of emotional changes, providing a valuable window into one's cognitive and mental state. Yet, the scarcity of labelled data in ambulatory studies prevents the reliable training of ML models, which usually rely on "data-hungry" distribution-based learning. Leveraging the abundance of labelled speech data from acted emotions, this paper proposes a few-shot learning approach for automatically recognizing emotion in spontaneous speech from a small number of labelled samples. Few-shot learning is implemented via a metric learning approach through a siamese neural network, which models the relative distance between samples rather than relying on learning absolute patterns of the corresponding distributions of each emotion. Results indicate the feasibility of the proposed metric learning in recognizing emotions from spontaneous speech in four datasets, even with a small amount of labelled samples. They further demonstrate superior performance of the proposed metric learning compared to commonly used adaptation methods, including network fine-tuning and adversarial learning. Findings from this work provide a foundation for the ambulatory tracking of human emotion in spontaneous speech contributing to the real-life assessment of mental health degradation.

* IEEE Transactions on Affective Computing, early access article. doi: 10.1109/TAFFC.2021.3109485 

  Access Paper or Ask Questions