Documentation errors increase healthcare costs and cause unnecessary patient deaths. As the standard language for diagnoses and billing, ICD codes serve as the foundation for medical documentation worldwide. Despite the prevalence of electronic medical records, hospitals still witness high levels of ICD miscoding. In this paper, we propose to automatically document ICD codes with far-field speech recognition. Far-field speech occurs when the microphone is located several meters from the source, as is common with smart homes and security systems. Our method combines acoustic signal processing with recurrent neural networks to recognize and document ICD codes in real time. To evaluate our model, we collected a far-field speech dataset of ICD-10 codes and found our model to achieve 87% accuracy with a BLEU score of 85%. By sampling from an unsupervised medical language model, our method is able to outperform existing methods. Overall, this work shows the potential of automatic speech recognition to provide efficient, accurate, and cost-effective healthcare documentation.
Machine learning models need to provide contrastive explanations, since people often seek to understand why a puzzling prediction occurred instead of some expected outcome. Current contrastive explanations are rudimentary comparisons between examples or raw features, which remain difficult to interpret, since they lack semantic meaning. We argue that explanations must be more relatable to other concepts, hypotheticals, and associations. Inspired by the perceptual process from cognitive psychology, we propose the XAI Perceptual Processing Framework and RexNet model for relatable explainable AI with Contrastive Saliency, Counterfactual Synthetic, and Contrastive Cues explanations. We investigated the application of vocal emotion recognition, and implemented a modular multi-task deep neural network to predict and explain emotions from speech. From think-aloud and controlled studies, we found that counterfactual explanations were useful and further enhanced with semantic cues, but not saliency explanations. This work provides insights into providing and evaluating relatable contrastive explainable AI for perception applications.
This study tackles unsupervised subword modeling in the zero-resource scenario, learning frame-level speech representation that is phonetically discriminative and speaker-invariant, using only untranscribed speech for target languages. Frame label acquisition is an essential step in solving this problem. High quality frame labels should be in good consistency with golden transcriptions and robust to speaker variation. We propose to improve frame label acquisition in our previously adopted deep neural network-bottleneck feature (DNN-BNF) architecture by applying the factorized hierarchical variational autoencoder (FHVAE). FHVAEs learn to disentangle linguistic content and speaker identity information encoded in speech. By discarding or unifying speaker information, speaker-invariant features are learned and fed as inputs to DPGMM frame clustering and DNN-BNF training. Experiments conducted on ZeroSpeech 2017 show that our proposed approaches achieve $2.4\%$ and $0.6\%$ absolute ABX error rate reductions in across- and within-speaker conditions, comparing to the baseline DNN-BNF system without applying FHVAEs. Our proposed approaches significantly outperform vocal tract length normalization in improving frame labeling and subword modeling.
Room acoustics measurements are used in many areas of audio research, from physical acoustics modelling and speech enhancement to virtual reality applications. This paper documents the technical specifications and choices made in the measurement of a dataset of spatial room impulse responses (SRIRs) in a variable acoustics room. Two spherical microphone arrays are used: the mh Acoustics Eigenmike em32 and the Zylia ZM-1, capable of up to fourth- and third-order Ambisonic capture, respectively. The dataset consists of three source and seven receiver positions, repeated with five configurations of the room's acoustics with varying levels of reverberation. Possible applications of the dataset include six degrees-of-freedom (6DoF) analysis and rendering, SRIR interpolation methods, and spatial dereverberation techniques.
Advanced neural network models have penetrated Automatic Speech Recognition (ASR) in recent years, however, in language modeling many systems still rely on traditional Back-off N-gram Language Models (BNLM) partly or entirely. The reason for this are the high cost and complexity of training and using neural language models, mostly possible by adding a second decoding pass (rescoring). In our recent work we have significantly improved the online performance of a conversational speech transcription system by transferring knowledge from a Recurrent Neural Network Language Model (RNNLM) to the single pass BNLM with text generation based data augmentation. In the present paper we analyze the amount of transferable knowledge and demonstrate that the neural augmented LM (RNN-BNLM) can help to capture almost 50% of the knowledge of the RNNLM yet by dropping the second decoding pass and making the system real-time capable. We also systematically compare word and subword LMs and show that subword-based neural text augmentation can be especially beneficial in under-resourced conditions. In addition, we show that using the RNN-BNLM in the first pass followed by a neural second pass, offline ASR results can be even significantly improved.
Despite remarkable success in image-to-image translation that celebrates the advancements of generative adversarial networks (GANs), very limited attempts are known for video domain translation. We study the task of video-to-video translation in the context of visual speech generation, where the goal is to transform an input video of any spoken word to an output video of a different word. This is a multi-domain translation, where each word forms a domain of videos uttering this word. Adaptation of the state-of-the-art image-to-image translation model (StarGAN) to this setting falls short with a large vocabulary size. Instead we propose to use character encodings of the words and design a novel character-based GANs architecture for video-to-video translation called Visual Speech GAN (ViSpGAN). We are the first to demonstrate video-to-video translation with a vocabulary of 500 words.
Attention-based encoder-decoder model has achieved impressive results for both automatic speech recognition (ASR) and text-to-speech (TTS) tasks. This approach takes advantage of the memorization capacity of neural networks to learn the mapping from the input sequence to the output sequence from scratch, without the assumption of prior knowledge such as the alignments. However, this model is prone to overfitting, especially when the amount of training data is limited. Inspired by SpecAugment and BERT, in this paper, we propose a semantic mask based regularization for training such kind of end-to-end (E2E) model. The idea is to mask the input features corresponding to a particular output token, e.g., a word or a word-piece, in order to encourage the model to fill the token based on the contextual information. While this approach is applicable to the encoder-decoder framework with any type of neural network architecture, we study the transformer-based model for ASR in this work. We perform experiments on Librispeech 960h and TedLium2 data sets, and achieve the state-of-the-art performance on the test set in the scope of E2E models.
Responsive listening during face-to-face conversations is a critical element of social interaction and is well established in psychological research. Through non-verbal signals response to the speakers' words, intonations, or behaviors in real-time, listeners show how they are engaged in dialogue. In this work, we build the Responsive Listener Dataset (RLD), a conversation video corpus collected from the public resources featuring 67 speakers, 76 listeners with three different attitudes. We define the responsive listening head generation task as the synthesis of a non-verbal head with motions and expressions reacting to the multiple inputs, including the audio and visual signal of the speaker. Unlike speech-driven gesture or talking head generation, we introduce more modals in this task, hoping to benefit several research fields, including human-to-human interaction, video-to-video translation, cross-modal understanding, and generation. Furthermore, we release an attitude conditioned listening head generation baseline. Project page: \url{https://project.mhzhou.com/rld}.
Speech emotion recognition is a challenging task for three main reasons: 1) human emotion is abstract, which means it is hard to distinguish; 2) in general, human emotion can only be detected in some specific moments during a long utterance; 3) speech data with emotional labeling is usually limited. In this paper, we present a novel attention based fully convolutional network for speech emotion recognition. We employ fully convolutional network as it is able to handle variable-length speech, free of the demand of segmentation to keep critical information not lost. The proposed attention mechanism can make our model be aware of which time-frequency region of speech spectrogram is more emotion-relevant. Considering limited data, the transfer learning is also adapted to improve the accuracy. Especially, it's interesting to observe obvious improvement obtained with natural scene image based pre-trained model. Validated on the publicly available IEMOCAP corpus, the proposed model outperformed the state-of-the-art methods with a weighted accuracy of 70.4% and an unweighted accuracy of 63.9% respectively.
Although attention based end-to-end models have achieved promising performance in speech recognition, the multi-pass forward computation in beam-search increases inference time cost, which limits their practical applications. To address this issue, we propose a non-autoregressive end-to-end speech recognition system called LASO (listen attentively, and spell once). Because of the non-autoregressive property, LASO predicts a textual token in the sequence without the dependence on other tokens. Without beam-search, the one-pass propagation much reduces inference time cost of LASO. And because the model is based on the attention based feedforward structure, the computation can be implemented in parallel efficiently. We conduct experiments on publicly available Chinese dataset AISHELL-1. LASO achieves a character error rate of 6.4%, which outperforms the state-of-the-art autoregressive transformer model (6.7%). The average inference latency is 21 ms, which is 1/50 of the autoregressive transformer model.