Attention-based encoder-decoder neural network models have recently shown promising results in machine translation and speech recognition. In this work, we propose an attention-based neural network model for joint intent detection and slot filling, both of which are critical steps for many speech understanding and dialog systems. Unlike in machine translation and speech recognition, alignment is explicit in slot filling. We explore different strategies in incorporating this alignment information to the encoder-decoder framework. Learning from the attention mechanism in encoder-decoder model, we further propose introducing attention to the alignment-based RNN models. Such attentions provide additional information to the intent classification and slot label prediction. Our independent task models achieve state-of-the-art intent detection error rate and slot filling F1 score on the benchmark ATIS task. Our joint training model further obtains 0.56% absolute (23.8% relative) error reduction on intent detection and 0.23% absolute gain on slot filling over the independent task models.
Recent deep learning Text-to-Speech (TTS) systems have achieved impressive performance by generating speech close to human parity. However, they suffer from training stability issues as well as incorrect alignment of the intermediate acoustic representation with the input text sequence. In this work, we introduce Regotron, a regularized version of Tacotron2 which aims to alleviate the training issues and at the same time produce monotonic alignments. Our method augments the vanilla Tacotron2 objective function with an additional term, which penalizes non-monotonic alignments in the location-sensitive attention mechanism. By properly adjusting this regularization term we show that the loss curves become smoother, and at the same time Regotron consistently produces monotonic alignments in unseen examples even at an early stage (13\% of the total number of epochs) of its training process, whereas the fully converged Tacotron2 fails to do so. Moreover, our proposed regularization method has no additional computational overhead, while reducing common TTS mistakes and achieving slighlty improved speech naturalness according to subjective mean opinion scores (MOS) collected from 50 evaluators.
We present a neural-network-based fast diffuse room impulse response generator (FAST-RIR) for generating room impulse responses (RIRs) for a given acoustic environment. Our FAST-RIR takes rectangular room dimensions, listener and speaker positions, and reverberation time as inputs and generates specular and diffuse reflections for a given acoustic environment. Our FAST-RIR is capable of generating RIRs for a given input reverberation time with an average error of 0.02s. We evaluate our generated RIRs in automatic speech recognition (ASR) applications using Google Speech API, Microsoft Speech API, and Kaldi tools. We show that our proposed FAST-RIR with batch size 1 is 400 times faster than a state-of-the-art diffuse acoustic simulator (DAS) on a CPU and gives similar performance to DAS in ASR experiments. Our FAST-RIR is 12 times faster than an existing GPU-based RIR generator (gpuRIR). We show that our FAST-RIR outperforms gpuRIR by 2.5% in an AMI far-field ASR benchmark.
This paper proposes a method that allows for non-parallel multi-domain voice conversion (VC) by using a variant of generative adversarial networks (GANs) called StarGAN. The main features of our method, which we term StarGAN-VC, are as follows: First, it requires no parallel utterances, transcriptions, or time alignment procedures for speech generator training. Second, it can simultaneously learn mappings across multiple domains using a single generator network so that it can fully use available training data collected from multiple domains by capturing common latent features that can be shared across different domains. Third, it is able to generate converted speech signals quickly enough to allow real-time implementations and requires only several minutes of training examples to generate reasonably realistic-sounding speech. In this paper, we describe three formulations of StarGAN, including a newly introduced novel StarGAN variant called "Augmented classifier StarGAN (A-StarGAN)", and compare them in a non-parallel VC task. We also compare them with several baseline methods.
In this paper, we present DuTongChuan, a novel context-aware translation model for simultaneous interpreting. This model allows to constantly read streaming text from the Automatic Speech Recognition (ASR) model and simultaneously determine the boundaries of Information Units (IUs) one after another. The detected IU is then translated into a fluent translation with two simple yet effective decoding strategies: partial decoding and context-aware decoding. In practice, by controlling the granularity of IUs and the size of the context, we can get a good trade-off between latency and translation quality easily. Elaborate evaluation from human translators reveals that our system achieves promising translation quality (85.71% for Chinese-English, and 86.36% for English-Chinese), specially in the sense of surprisingly good discourse coherence. According to an End-to-End (speech-to-speech simultaneous interpreting) evaluation, this model presents impressive performance in reducing latency (to less than 3 seconds at most times). Furthermore, we successfully deploy this model in a variety of Baidu's products which have hundreds of millions of users, and we release it as a service in our AI platform.
Given the recent surge in developments of deep learning, this article provides a review of the state-of-the-art deep learning techniques for audio signal processing. Speech, music, and environmental sound processing are considered side-by-side, in order to point out similarities and differences between the domains, highlighting general methods, problems, key references, and potential for cross-fertilization between areas. The dominant feature representations (in particular, log-mel spectra and raw waveform) and deep learning models are reviewed, including convolutional neural networks, variants of the long short-term memory architecture, as well as more audio-specific neural network models. Subsequently, prominent deep learning application areas are covered, i.e. audio recognition (automatic speech recognition, music information retrieval, environmental sound detection, localization and tracking) and synthesis and transformation (source separation, audio enhancement, generative models for speech, sound, and music synthesis). Finally, key issues and future questions regarding deep learning applied to audio signal processing are identified.
Computers still have a long way to go before they can interact with users in a truly natural fashion. From a users perspective, the most natural way to interact with a computer would be through a speech and gesture interface. Although speech recognition has made significant advances in the past ten years, gesture recognition has been lagging behind. Sign Languages (SL) are the most accomplished forms of gestural communication. Therefore, their automatic analysis is a real challenge, which is interestingly implied to their lexical and syntactic organization levels. Statements dealing with sign language occupy a significant interest in the Automatic Natural Language Processing (ANLP) domain. In this work, we are dealing with sign language recognition, in particular of French Sign Language (FSL). FSL has its own specificities, such as the simultaneity of several parameters, the important role of the facial expression or movement and the use of space for the proper utterance organization. Unlike speech recognition, Frensh sign language (FSL) events occur both sequentially and simultaneously. Thus, the computational processing of FSL is too complex than the spoken languages. We present a novel approach based on HMM to reduce the recognition complexity.
Large-scale auto-regressive language models pretrained on massive text have demonstrated their impressive ability to perform new natural language tasks with only a few text examples, without the need for fine-tuning. Recent studies further show that such a few-shot learning ability can be extended to the text-image setting by training an encoder to encode the images into embeddings functioning like the text embeddings of the language model. Interested in exploring the possibility of transferring the few-shot learning ability to the audio-text setting, we propose a novel speech understanding framework, WavPrompt, where we finetune a wav2vec model to generate a sequence of audio embeddings understood by the language model. We show that WavPrompt is a few-shot learner that can perform speech understanding tasks better than a naive text baseline. We conduct detailed ablation studies on different components and hyperparameters to empirically identify the best model configuration. In addition, we conduct a non-speech understanding experiment to show WavPrompt can extract more information than just the transcriptions. Code is available at https://github.com/Hertin/WavPrompt