We present a voice conversion framework that converts normal speech into dysarthric speech while preserving the speaker identity. Such a framework is essential for (1) clinical decision making processes and alleviation of patient stress, (2) data augmentation for dysarthric speech recognition. This is an especially challenging task since the converted samples should capture the severity of dysarthric speech while being highly natural and possessing the speaker identity of the normal speaker. To this end, we adopted a two-stage framework, which consists of a sequence-to-sequence model and a nonparallel frame-wise model. Objective and subjective evaluations were conducted on the UASpeech dataset, and results showed that the method was able to yield reasonable naturalness and capture severity aspects of the pathological speech. On the other hand, the similarity to the normal source speaker's voice was limited and requires further improvements.
Automatic Speech Recognition (ASR) systems generally do not produce punctuated transcripts. To make transcripts more readable and follow the expected input format for downstream language models, it is necessary to add punctuation marks. In this paper, we tackle the punctuation restoration problem specifically for the noisy text (e.g., phone conversation scenarios). To leverage the available written text datasets, we introduce a data sampling technique based on an n-gram language model to sample more training data that are similar to our in-domain data. Moreover, we propose a two-stage fine-tuning approach that utilizes the sampled external data as well as our in-domain dataset for models based on BERT. Extensive experiments show that the proposed approach outperforms the baseline with an improvement of 1:12% F1 score.
While permutation invariant training (PIT) based continuous speech separation (CSS) significantly improves the conversation transcription accuracy, it often suffers from speech leakages and failures in separation at "hot spot" regions because it has a fixed number of output channels. In this paper, we propose to apply recurrent selective attention network (RSAN) to CSS, which generates a variable number of output channels based on active speaker counting. In addition, we propose a novel block-wise dependency extension of RSAN by introducing dependencies between adjacent processing blocks in the CSS framework. It enables the network to utilize the separation results from the previous blocks to facilitate the current block processing. Experimental results on the LibriCSS dataset show that the RSAN-based CSS (RSAN-CSS) network consistently improves the speech recognition accuracy over PIT-based models. The proposed block-wise dependency modeling further boosts the performance of RSAN-CSS.
Transformer-based models have proven to be powerful in many natural language, computer vision, and speech recognition applications. It is expensive to train these types of models due to unfixed input length, complex computation, and large numbers of parameters. Existing systems either only focus on efficient inference or optimize only BERT-like encoder models. In this paper, we present LightSeq2, a system for efficient training of Transformer-based models on GPUs. We propose a series of GPU optimization techniques tailored to computation flow and memory access patterns of neural layers in Transformers. LightSeq2 supports a variety of network architectures, including BERT (encoder-only), GPT (decoder-only), and Transformer (encoder-decoder). Our experiments on GPUs with varying models and datasets show that LightSeq2 is 1.4-3.5x faster than previous systems. In particular, it gains 308% training speedup compared with existing systems on a large public machine translation benchmark (WMT14 English-German).
Automatic Speech Recognition (ASR) systems are often optimized to work best for speakers with canonical speech patterns. Unfortunately, these systems perform poorly when tested on atypical speech and heavily accented speech. It has previously been shown that personalization through model fine-tuning substantially improves performance. However, maintaining such large models per speaker is costly and difficult to scale. We show that by adding a relatively small number of extra parameters to the encoder layers via so-called residual adapter, we can achieve similar adaptation gains compared to model fine-tuning, while only updating a tiny fraction (less than 0.5%) of the model parameters. We demonstrate this on two speech adaptation tasks (atypical and accented speech) and for two state-of-the-art ASR architectures.
Time masking has become a de facto augmentation technique for speech and audio tasks, including automatic speech recognition (ASR) and audio classification, most notably as a part of SpecAugment. In this work, we propose SpliceOut, a simple modification to time masking which makes it computationally more efficient. SpliceOut performs comparably to (and sometimes outperforms) SpecAugment on a wide variety of speech and audio tasks, including ASR for seven different languages using varying amounts of training data, as well as on speech translation, sound and music classification, thus establishing itself as a broadly applicable audio augmentation method. SpliceOut also provides additional gains when used in conjunction with other augmentation techniques. Apart from the fully-supervised setting, we also demonstrate that SpliceOut can complement unsupervised representation learning with performance gains in the semi-supervised and self-supervised settings.
Emotion recognition from speech is one of the key steps towards emotional intelligence in advanced human-machine interaction. Identifying emotions in human speech requires learning features that are robust and discriminative across diverse domains that differ in terms of language, spontaneity of speech, recording conditions, and types of emotions. This corresponds to a learning scenario in which the joint distributions of features and labels may change substantially across domains. In this paper, we propose a deep architecture that jointly exploits a convolutional network for extracting domain-shared features and a long short-term memory network for classifying emotions using domain-specific features. We use transferable features to enable model adaptation from multiple source domains, given the sparseness of speech emotion data and the fact that target domains are short of labeled data. A comprehensive cross-corpora experiment with diverse speech emotion domains reveals that transferable features provide gains ranging from 4.3% to 18.4% in speech emotion recognition. We evaluate several domain adaptation approaches, and we perform an ablation study to understand which source domains add the most to the overall recognition effectiveness for a given target domain.
Information integration from different modalities is an active area of research. Human beings and, in general, biological neural systems are quite adept at using a multitude of signals from different sensory perceptive fields to interact with the environment and each other. Recent work in deep fusion models via neural networks has led to substantial improvements over unimodal approaches in areas like speech recognition, emotion recognition and analysis, captioning and image description. However, such research has mostly focused on architectural changes allowing for fusion of different modalities while keeping the model complexity manageable. Inspired by recent neuroscience ideas about multisensory integration and processing, we investigate the effect of synergy maximizing loss functions. Experiments on multimodal sentiment analysis tasks: CMU-MOSI and CMU-MOSEI with different models show that our approach provides a consistent performance boost.
Deepspeech was very useful for development IoT devices that need voice recognition. One of the voice recognition systems is deepspeech from Mozilla. Deepspeech is an open-source voice recognition that was using a neural network to convert speech spectrogram into a text transcript. This paper shows the implementation process of speech recognition on a low-end computational device. Development of English-language speech recognition that has many datasets become a good point for starting. The model that used results from pre-trained model that provide by each version of deepspeech, without change of the model that already released, furthermore the benefit of using raspberry pi as a media end-to-end speech recognition device become a good thing, user can change and modify of the speech recognition, and also deepspeech can be standalone device without need continuously internet connection to process speech recognition, and even this paper show the power of Tensorflow Lite can make a significant difference on inference by deepspeech rather than using Tensorflow non-Lite.This paper shows the experiment using Deepspeech version 0.1.0, 0.1.1, and 0.6.0, and there is some improvement on Deepspeech version 0.6.0, faster while processing speech-to-text on old hardware raspberry pi 3 b+.
Speech data is notoriously difficult to work with due to a variety of codecs, lengths of recordings, and meta-data formats. We present Lhotse, a speech data representation library that draws upon lessons learned from Kaldi speech recognition toolkit and brings its concepts into the modern deep learning ecosystem. Lhotse provides a common JSON description format with corresponding Python classes and data preparation recipes for over 30 popular speech corpora. Various datasets can be easily combined together and re-purposed for different tasks. The library handles multi-channel recordings, long recordings, local and cloud storage, lazy and on-the-fly operations amongst other features. We introduce Cut and CutSet concepts, which simplify common data wrangling tasks for audio and help incorporate acoustic context of speech utterances. Finally, we show how Lhotse leverages PyTorch data API abstractions and adopts them to handle speech data for deep learning.