Electrical Engineering And Systems Science

In this work, we propose an acoustic embedding based approach for representation learning in speech recognition. The proposed approach involves two stages comprising of acoustic filterbank learning from raw waveform, followed by modulation filterbank learning. In each stage, a relevance weighting operation is employed that acts as a feature selection module. In particular, the relevance weighting network receives embeddings of the model outputs from the previous time instants as feedback. The proposed relevance weighting scheme allows the respective feature representations to be adaptively selected before propagation to the higher layers. The application of the proposed approach for the task of speech recognition on Aurora-4 and CHiME-3 datasets gives significant performance improvements over baseline systems on raw waveform signal as well as those based on mel representations (average relative improvement of 15% over the mel baseline on Aurora-4 dataset and 7% on CHiME-3 dataset).

The ResNet-based architecture has been widely adopted to extract speaker embeddings for text-independent speaker verification systems. By introducing the residual connections to the CNN and standardizing the residual blocks, the ResNet structure is capable of training deep networks to achieve highly competitive recognition performance. However, when the input feature space becomes more complicated, simply increasing the depth and width of the ResNet network may not fully realize its performance potential. In this paper, we present two extensions of the ResNet architecture, ResNeXt and Res2Net, for speaker verification. Originally proposed for image recognition, the ResNeXt and Res2Net introduce two more dimensions, cardinality and scale, in addition to depth and width, to improve the model's representation capacity. By increasing the scale dimension, the Res2Net model can represent multi-scale features with various granularities, which particularly facilitates speaker verification for short utterances. We evaluate our proposed systems on three speaker verification tasks. Experiments on the VoxCeleb test set demonstrated that the ResNeXt and Res2Net can significantly outperform the conventional ResNet model. The Res2Net model achieved superior performance by reducing the EER by 18.5% relative. Experiments on the other two internal test sets of mismatched conditions further confirmed the generalization of the ResNeXt and Res2Net architectures against noisy environment and segment length variations.

While machine learning techniques are traditionally resource intensive, we are currently witnessing an increased interest in hardware and energy efficient approaches. This need for resource-efficient machine learning is primarily driven by the demand for embedded systems and their usage in ubiquitous computing and IoT applications. In this article, we provide a resource-efficient approach for multi-channel speech enhancement based on Deep Neural Networks (DNNs). In particular, we use reduced-precision DNNs for estimating a speech mask from noisy, multi-channel microphone observations. This speech mask is used to obtain either the Minimum Variance Distortionless Response (MVDR) or Generalized Eigenvalue (GEV) beamformer. In the extreme case of binary weights and reduced precision activations, a significant reduction of execution time and memory footprint is possible while still obtaining an audio quality almost on par to single-precision DNNs and a slightly larger Word Error Rate (WER) for single speaker scenarios using the WSJ0 speech corpus.

Developing a reliable sound detection and recognition system offers many benefits and has many useful applications in different industries. This paper examines the difficulties that exist when attempting to perform sound classification as it relates to respiratory disease classification. Some methods which have been employed such as independent component analysis and blind source separation are examined. Finally, an examination on the use of deep learning and long short-term memory networks is performed in order to identify how such a task can be implemented.

X-vectors have become the standard for speaker-embeddings in automatic speaker verification. X-vectors are obtained using a Time-delay Neural Network (TDNN) with context over several frames. We have explored the use of an architecture built on self-attention which attends to all the features over the entire utterance, and hence better capture speaker-level characteristics. We have used the encoder structure of Transformers, which is built on self-attention, as the base architecture and trained it to do a speaker classification task. In this paper, we have proposed to derive speaker embeddings from the output of the trained Transformer encoder structure after appropriate statistics pooling to obtain utterance level features. We have named the speaker embeddings from this structure as s-vectors. s-vectors outperform x-vectors with a relative improvement of 10% and 15% in % EER when trained on Voxceleb-1 only and Voxceleb-1+2 datasets. We have also investigated the effect of deriving s-vectors from different layers of the model.

Most existing deep learning based binaural speaker separation systems focus on producing a monaural estimate for each of the target speakers, and thus do not preserve the interaural cues, which are crucial for human listeners to perform sound localization and lateralization. In this study, we address talker-independent binaural speaker separation with interaural cues preserved in the estimated binaural signals. Specifically, we extend a newly-developed gated recurrent neural network for monaural separation by additionally incorporating self-attention mechanisms and dense connectivity. We develop an end-to-end multiple-input multiple-output system, which directly maps from the binaural waveform of the mixture to those of the speech signals. The experimental results show that our proposed approach achieves significantly better separation performance than a recent binaural separation approach. In addition, our approach effectively preserves the interaural cues, which improves the accuracy of sound localization.

We explore the possibility of leveraging accelerometer data to perform speech enhancement in very noisy conditions. Although it is possible to only partially reconstruct user's speech from the accelerometer, the latter provides a strong conditioning signal that is not influenced from noise sources in the environment. Based on this observation, we feed a multi-modal input to SEANet (Sound EnhAncement Network), a wave-to-wave fully convolutional model, which adopts a combination of feature losses and adversarial losses to reconstruct an enhanced version of user's speech. We trained our model with data collected by sensors mounted on an earbud and synthetically corrupted by adding different kinds of noise sources to the audio signal. Our experimental results demonstrate that it is possible to achieve very high quality results, even in the case of interfering speech at the same level of loudness. A sample of the output produced by our model is available at this https URL.

The ability to automatically detect stuttering events in speech could help speech pathologists track an individual's fluency over time or help improve speech recognition systems for people with atypical speech patterns. Despite increasing interest in this area, existing public datasets are too small to build generalizable dysfluency detection systems and lack sufficient annotations. In this work, we introduce Stuttering Events in Podcasts (SEP-28k), a dataset containing over 28k clips labeled with five event types including blocks, prolongations, sound repetitions, word repetitions, and interjections. Audio comes from public podcasts largely consisting of people who stutter interviewing other people who stutter. We benchmark a set of acoustic models on SEP-28k and the public FluencyBank dataset and highlight how simply increasing the amount of training data improves relative detection performance by 28\% and 24\% F1 on each. Annotations from over 32k clips across both datasets will be publicly released.

A speech separation task can be roughly divided into audio-only separation and audio-visual separation. In order to make speech separation technology applied in the real scenario of the disabled, this paper presents an extended speech separation problem which refers in particular to sign language assisted speech separation. However, most existing datasets for speech separation are audios and videos which contain audio and/or visual modalities. To address the extended speech separation problem, we introduce a large-scale dataset named Sign Language News Speech (SLNSpeech) dataset in which three modalities of audio, visual, and sign language are coexisted. Then, we design a general deep learning network for the self-supervised learning of three modalities, particularly, using sign language embeddings together with audio or audio-visual information for better solving the speech separation task. Specifically, we use 3D residual convolutional network to extract sign language features and use pretrained VGGNet model to exact visual features. After that, an improved U-Net with skip connections in feature extraction stage is applied for learning the embeddings among the mixed spectrogram transformed from source audios, the sign language features and visual features. Experiments results show that, besides visual modality, sign language modality can also be used alone to supervise speech separation task. Moreover, we also show the effectiveness of sign language assisted speech separation when the visual modality is disturbed. Source code will be released in http://cheertt.top/homepage/

The assessment of music performances in most cases takes into account the underlying musical score being performed. While there have been several automatic approaches for objective music performance assessment (MPA) based on extracted features from both the performance audio and the score, deep neural network-based methods incorporating score information into MPA models have not yet been investigated. In this paper, we introduce three different models capable of score-informed performance assessment. These are (i) a convolutional neural network that utilizes a simple time-series input comprising of aligned pitch contours and score, (ii) a joint embedding model which learns a joint latent space for pitch contours and scores, and (iii) a distance matrix-based convolutional neural network which utilizes patterns in the distance matrix between pitch contours and musical score to predict assessment ratings. Our results provide insights into the suitability of different architectures and input representations and demonstrate the benefits of score-informed models as compared to score-independent models.