MERL
Abstract:In contrast with previous approaches where information flows only towards deeper layers of a stack, we consider a multi-pass transformer (MPT) architecture in which earlier layers are allowed to process information in light of the output of later layers. To maintain a directed acyclic graph structure, the encoder stack of a transformer is repeated along a new multi-pass dimension, keeping the parameters tied, and information is allowed to proceed unidirectionally both towards deeper layers within an encoder stack and towards any layer of subsequent stacks. We consider both soft (i.e., continuous) and hard (i.e., discrete) connections between parallel encoder stacks, relying on a neural architecture search to find the best connection pattern in the hard case. We perform an extensive ablation study of the proposed MPT architecture and compare it with other state-of-the-art transformer architectures. Surprisingly, Base Transformer equipped with MPT can surpass the performance of Large Transformer on the challenging machine translation En-De and En-Fr datasets. In the hard connection case, the optimal connection pattern found for En-De also leads to improved performance for En-Fr.
Abstract:Clipping the gradient is a known approach to improving gradient descent, but requires hand selection of a clipping threshold hyperparameter. We present AutoClip, a simple method for automatically and adaptively choosing a gradient clipping threshold, based on the history of gradient norms observed during training. Experimental results show that applying AutoClip results in improved generalization performance for audio source separation networks. Observation of the training dynamics of a separation network trained with and without AutoClip show that AutoClip guides optimization into smoother parts of the loss landscape. AutoClip is very simple to implement and can be integrated readily into a variety of applications across multiple domains.
Abstract:The Audio-Visual Scene-aware Dialog (AVSD) task requires an agent to indulge in a natural conversation with a human about a given video. Specifically, apart from the video frames, the agent receives the audio, brief captions, and a dialog history, and the task is to produce the correct answer to a question about the video. Due to the diversity in the type of inputs, this task poses a very challenging multimodal reasoning problem. Current approaches to AVSD either use global video-level features or those from a few sampled frames, and thus lack the ability to explicitly capture relevant visual regions or their interactions for answer generation. To this end, we propose a novel spatio-temporal scene graph representation (STSGR) modeling fine-grained information flows within videos. Specifically, on an input video sequence, STSGR (i) creates a two-stream visual and semantic scene graph on every frame, (ii) conducts intra-graph reasoning using node and edge convolutions generating visual memories, and (iii) applies inter-graph aggregation to capture their temporal evolutions. These visual memories are then combined with other modalities and the question embeddings using a novel semantics-controlled multi-head shuffled transformer, which then produces the answer recursively. Our entire pipeline is trained end-to-end. We present experiments on the AVSD dataset and demonstrate state-of-the-art results. A human evaluation on the quality of our generated answers shows 12% relative improvement against prior methods.
Abstract:Various adversarial audio attacks have recently been developed to fool automatic speech recognition (ASR) systems. We here propose a defense against such attacks based on the uncertainty introduced by dropout in neural networks. We show that our defense is able to detect attacks created through optimized perturbations and frequency masking on a state-of-the-art end-to-end ASR system. Furthermore, the defense can be made robust against attacks that are immune to noise reduction. We test our defense on Mozilla's CommonVoice dataset, the UrbanSound dataset, and an excerpt of the LibriSpeech dataset, showing that it achieves high detection accuracy in a wide range of scenarios.
Abstract:We propose an unsupervised speaker adaptation method inspired by the neural Turing machine for end-to-end (E2E) automatic speech recognition (ASR). The proposed model contains a memory block that holds speaker i-vectors extracted from the training data and reads relevant i-vectors from the memory through an attention mechanism. The resulting memory vector (M-vector) is concatenated to the acoustic features or to the hidden layer activations of an E2E neural network model. The E2E ASR system is based on the joint connectionist temporal classification and attention-based encoder-decoder architecture. M-vector and i-vector results are compared for inserting them at different layers of the encoder neural network using the WSJ and TED-LIUM2 ASR benchmarks. We show that M-vectors, which do not require an auxiliary speaker embedding extraction system at test time, achieve similar word error rates (WERs) compared to i-vectors for single speaker utterances and significantly lower WERs for utterances in which there are speaker changes.
Abstract: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.
Abstract:Encoder-decoder based sequence-to-sequence models have demonstrated state-of-the-art results in end-to-end automatic speech recognition (ASR). Recently, the transformer architecture, which uses self-attention to model temporal context information, has been shown to achieve significantly lower word error rates (WERs) compared to recurrent neural network (RNN) based system architectures. Despite its success, the practical usage is limited to offline ASR tasks, since encoder-decoder architectures typically require an entire speech utterance as input. In this work, we propose a transformer based end-to-end ASR system for streaming ASR, where an output must be generated shortly after each spoken word. To achieve this, we apply time-restricted self-attention for the encoder and triggered attention for the encoder-decoder attention mechanism. Our proposed streaming transformer architecture achieves 2.7% and 7.0% WER for the "clean" and "other" test data of LibriSpeech, which to our knowledge is the best published streaming end-to-end ASR result for this task.
Abstract:While there has been much recent progress using deep learning techniques to separate speech and music audio signals, these systems typically require large collections of isolated sources during the training process. When extending audio source separation algorithms to more general domains such as environmental monitoring, it may not be possible to obtain isolated signals for training. Here, we propose objective functions and network architectures that enable training a source separation system with weak labels. In this scenario, weak labels are defined in contrast with strong time-frequency (TF) labels such as those obtained from isolated sources, and refer either to frame-level weak labels where one only has access to the time periods when different sources are active in an audio mixture, or to clip-level weak labels that only indicate the presence or absence of sounds in an entire audio clip. We train a separator that estimates a TF mask for each type of sound event, using a sound event classifier as an assessor of the separator's performance to bridge the gap between the TF-level separation and the ground truth weak labels only available at the frame or clip level. Our objective function requires the classifier applied to a separated source to assign high probability to the class corresponding to that source and low probability to all other classes. The objective function also enforces that the separated sources sum up to the mixture. We benchmark the performance of our algorithm using synthetic mixtures of overlapping events created from a database of sounds recorded in urban environments. Compared to training a network using isolated sources, our model achieves somewhat lower but still significant SI-SDR improvement, even in scenarios with significant sound event overlap.
Abstract:Separating an audio scene such as a cocktail party into constituent, meaningful components is a core task in computer audition. Deep networks are the state-of-the-art approach. They are trained on synthetic mixtures of audio made from isolated sound source recordings so that ground truth for the separation is known. However, the vast majority of available audio is not isolated. The brain uses primitive cues that are independent of the characteristics of any particular sound source to perform an initial segmentation of the audio scene. We present a method for bootstrapping a deep model for music source separation without ground truth by using multiple primitive cues. We apply our method to train a network on a large set of unlabeled music recordings from YouTube to separate vocals from accompaniment without the need for ground truth isolated sources or artificial training mixtures.
Abstract:Recently, the end-to-end approach has proven its efficacy in monaural multi-speaker speech recognition. However, high word error rates (WERs) still prevent these systems from being used in practical applications. On the other hand, the spatial information in multi-channel signals has proven helpful in far-field speech recognition tasks. In this work, we propose a novel neural sequence-to-sequence (seq2seq) architecture, MIMO-Speech, which extends the original seq2seq to deal with multi-channel input and multi-channel output so that it can fully model multi-channel multi-speaker speech separation and recognition. MIMO-Speech is a fully neural end-to-end framework, which is optimized only via an ASR criterion. It is comprised of: 1) a monaural masking network, 2) a multi-source neural beamformer, and 3) a multi-output speech recognition model. With this processing, the input overlapped speech is directly mapped to text sequences. We further adopted a curriculum learning strategy, making the best use of the training set to improve the performance. The experiments on the spatialized wsj1-2mix corpus show that our model can achieve more than 60% WER reduction compared to the single-channel system with high quality enhanced signals (SI-SDR = 23.1 dB) obtained by the above separation function.