We propose improved Deep Neural Network (DNN) training loss functions for more accurate single keyword spotting on resource-constrained embedded devices. The loss function modifications consist of a combination of multi-task training and weighted cross entropy. In the multi-task architecture, the keyword DNN acoustic model is trained with two tasks in parallel-the main task of predicting the keyword-specific phone states, and an auxiliary task of predicting LVCSR senones. We show that multi-task learning leads to comparable accuracy over a previously proposed transfer learning approach where the keyword DNN training is initialized by an LVCSR DNN of the same input and hidden layer sizes. The combination of LVCSRinitialization and Multi-task training gives improved keyword detection accuracy compared to either technique alone. We also propose modifying the loss function to give a higher weight on input frames corresponding to keyword phone targets, with a motivation to balance the keyword and background training data. We show that weighted cross-entropy results in additional accuracy improvements. Finally, we show that the combination of 3 techniques-LVCSR-initialization, multi-task training and weighted cross-entropy gives the best results, with significantly lower False Alarm Rate than the LVCSR-initialization technique alone, across a wide range of Miss Rates.

Emotion recognition is a challenging task due to limited availability of in-the-wild labeled datasets. Self-supervised learning has shown improvements on tasks with limited labeled datasets in domains like speech and natural language. Models such as BERT learn to incorporate context in word embeddings, which translates to improved performance in downstream tasks like question answering. In this work, we extend self-supervised training to multi-modal applications. We learn multi-modal representations using a transformer trained on the masked language modeling task with audio, visual and text features. This model is fine-tuned on the downstream task of emotion recognition. Our results on the CMU-MOSEI dataset show that this pre-training technique can improve the emotion recognition performance by up to 3% compared to the baseline.

This paper presents an audio visual automatic speech recognition (AV-ASR) system using a Transformer-based architecture. We particularly focus on the scene context provided by the visual information, to ground the ASR. We extract representations for audio features in the encoder layers of the transformer and fuse video features using an additional crossmodal multihead attention layer. Additionally, we incorporate a multitask training criterion for multiresolution ASR, where we train the model to generate both character and subword level transcriptions. Experimental results on the How2 dataset, indicate that multiresolution training can speed up convergence by around 50% and relatively improves word error rate (WER) performance by upto 18% over subword prediction models. Further, incorporating visual information improves performance with relative gains upto 3.76% over audio only models. Our results are comparable to state-of-the-art Listen, Attend and Spell-based architectures.

General embeddings like word2vec, GloVe and ELMo have shown a lot of success in natural language tasks. The embeddings are typically extracted from models that are built on general tasks such as skip-gram models and natural language generation. In this paper, we extend the work from natural language understanding to multi-modal architectures that use audio, visual and textual information for machine learning tasks. The embeddings in our network are extracted using the encoder of a transformer model trained using multi-task training. We use person identification and automatic speech recognition as the tasks in our embedding generation framework. We tune and evaluate the embeddings on the downstream task of emotion recognition and demonstrate that on the CMU-MOSEI dataset, the embeddings can be used to improve over previous state of the art results.

Recent literature has shown that a learned front end with multi-channel audio input can outperform traditional beamforming algorithms for automatic speech recognition (ASR). In this paper, we present our study on multi-channel acoustic modeling using OPUS compression with different bitrates for the different channels. We analyze the degradation in word error rate (WER) as a function of the audio encoding bitrate and show that the WER degrades by 12.6% relative with 16kpbs as compared to uncompressed audio. We show that its always preferable to have a multi-channel audio input over a single channel audio input given limited bandwidth. Our results show that for the best WER, when one of the two channels can be encoded with a bitrate higher than 32kbps, its optimal to encode the other channel with the highest bitrate possible. For bitrates lower than that, its preferable to distribute the bitrate equally between the two channels. We further show that by training the acoustic model on mixed bitrate input, upto 50% of the degradation can be recovered using a single model.

No abstract

We present a Conformer-based end-to-end neural diarization (EEND) model that uses both acoustic input and features derived from an automatic speech recognition (ASR) model. Two categories of features are explored: features derived directly from ASR output (phones, position-in-word and word boundaries) and features derived from a lexical speaker change detection model, trained by fine-tuning a pretrained BERT model on the ASR output. Three modifications to the Conformer-based EEND architecture are proposed to incorporate the features. First, ASR features are concatenated with acoustic features. Second, we propose a new attention mechanism called contextualized self-attention that utilizes ASR features to build robust speaker representations. Finally, multi-task learning is used to train the model to minimize classification loss for the ASR features along with diarization loss. Experiments on the two-speaker English conversations of Switchboard+SRE data sets show that multi-task learning with position-in-word information is the most effective way of utilizing ASR features, reducing the diarization error rate (DER) by 20\% relative to the baseline.

In this paper, we test the hypothesis that interesting events in unstructured videos are inherently audiovisual. We combine deep image representations for object recognition and scene understanding with representations from an audiovisual affect recognition model. To this set, we include content agnostic audio-visual synchrony representations and mel-frequency cepstral coefficients to capture other intrinsic properties of audio. These features are used in a modular supervised model. We present results from two experiments: efficacy study of single features on the task, and an ablation study where we leave one feature out at a time. For the video summarization task, our results indicate that the visual features carry most information, and including audiovisual features improves over visual-only information. To better study the task of highlight detection, we run a pilot experiment with highlights annotations for a small subset of video clips and fine-tune our best model on it. Results indicate that we can transfer knowledge from the video summarization task to a model trained specifically for the task of highlight detection.