Predicting the intelligibility of noisy recordings is difficult and most current algorithms treat all speech energy as equally important to intelligibility. Our previous work on human perception used a listening test paradigm and correlational analysis to show that some energy is more important to intelligibility than other energy. In this paper, we propose a system called the Bubble Cooperative Network (BCN), which aims to predict important areas of individual utterances directly from clean speech. Given such a prediction, noise is added to the utterance in unimportant regions and then presented to a recognizer. The BCN is trained with a loss that encourages it to add as much noise as possible while preserving recognition performance, encouraging it to identify important regions precisely and place the noise everywhere else. Empirical evaluation shows that the BCN can obscure 97.7% of the spectrogram with noise while maintaining recognition accuracy for a simple speech recognizer that compares a noisy test utterance with a clean reference utterance. The masks predicted by a single BCN on several utterances show patterns that are similar to analyses derived from human listening tests that analyze each utterance separately, while exhibiting better generalization and less context-dependence than previous approaches.
more »
« less
Identifying Important Time-Frequency Locations in Continuous Speech Utterances
Human listeners use specific cues to recognize speech and recent experiments have shown that certain time-frequency regions of individual utterances are more important to their correct identification than others. A model that could identify such cues or regions from clean speech would facilitate speech recognition and speech enhancement by focusing on those important regions. Thus, in this paper we present a model that can predict the regions of individual utterances that are important to an automatic speech recognition (ASR) “listener” by learning to add as much noise as possible to these utterances while still permitting the ASR to correctly identify them. This work utilizes a continuous speech recognizer to recognize multi-word utterances and builds upon our previous work that performed the same process for an isolated word recognizer. Our experimental results indicate that our model can apply noise to obscure 90.5% of the spectrogram while leaving recognition performance nearly unchanged.
more »
« less
- Award ID(s):
- 1750383
- PAR ID:
- 10277023
- Date Published:
- Journal Name:
- Proceedings of Interspeech
- Page Range / eLocation ID:
- 1639 to 1643
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
null (Ed.)This paper proposes a metric that we call the structured saliency benchmark (SSBM) to evaluate importance maps computed for automatic speech recognizers on individual utterances. These maps indicate time-frequency points of the utterance that are most important for correct recognition of a target word. Our evaluation technique is not only suitable for standard classification tasks, but is also appropriate for structured prediction tasks like sequence-to-sequence models. Additionally, we use this approach to perform a comparison of the importance maps created by our previously introduced technique using “bubble noise” to identify important points through correlation with a baseline approach based on smoothed speech energy and forced alignment. Our results show that the bubble analysis approach is better at identifying important speech regions than this baseline on 100 sentences from the AMI corpus.more » « less
-
more » « less
In clinical settings, most automatic recognition systems use visual or sensory data to recognize activities. These systems cannot recognize activities that rely on verbal assessment, lack visual cues, or do not use medical devices. We examined speech-based activity and activity-stage recognition in a clinical domain, making the following contributions. (1) We collected a high-quality dataset representing common activities and activity stages during actual trauma resuscitation events-the initial evaluation and treatment of critically injured patients. (2) We introduced a novel multimodal network based on audio signal and a set of keywords that does not require a high-performing automatic speech recognition (ASR) engine. (3) We designed novel contextual modules to capture dynamic dependencies in team conversations about activities and stages during a complex workflow. (4) We introduced a data augmentation method, which simulates team communication by combining selected utterances and their audio clips, and showed that this method contributed to performance improvement in our data-limited scenario. In offline experiments, our proposed context-aware multimodal model achieved F1-scores of 73.2±0.8% and 78.1±1.1% for activity and activity-stage recognition, respectively. In online experiments, the performance declined about 10% for both recognition types when using utterance-level segmentation of the ASR output. The performance declined about 15% when we omitted the utterance-level segmentation. Our experiments showed the feasibility of speech-based activity and activity-stage recognition during dynamic clinical events.
-
Say What? Automatic Modeling of Collaborative Problem Solving Skills from Student Speech in the WildWe investigated the feasibility of using automatic speech recognition (ASR) and natural language processing (NLP) to classify collaborative problem solving (CPS) skills from recorded speech in noisy environments. We analyzed data from 44 dyads of middle and high school students who used videoconferencing to collaboratively solve physics and math problems (35 and 9 dyads in school and lab environments, respectively). Trained coders identified seven cognitive and social CPS skills (e.g., sharing information) in 8,660 utterances. We used a state-of-theart deep transfer learning approach for NLP, Bidirectional Encoder Representations from Transformers (BERT), with a special input representation enabling the model to analyze adjacent utterances for contextual cues. We achieved a microaverage AUROC score (across seven CPS skills) of .80 using ASR transcripts, compared to .91 for human transcripts, indicating a decrease in performance attributable to ASR error. We found that the noisy school setting introduced additional ASR error, which reduced model performance (micro-average AUROC of .78) compared to the lab (AUROC = .83). We discuss implications for real-time CPS assessment and support in schools.more » « less
-
This paper describes experiments in training HMM-based text-to-speech (TTS) voices on data collected for Automatic Speech Recognition (ASR) training. We compare a number of filtering techniques designed to identify the best utterances from a noisy, multi-speaker corpus for training voices, to exclude speech containing noise and to include speech close in nature to more traditionally-collected TTS corpora. We also evaluate the use of automatic speech recognizers for intelligibility assessment in comparison with crowdsourcing methods. While the goal of this work is to develop natural-sounding and intelligible TTS voices in Low Resource Languages (LRLs) rapidly and easily, without the expense of recording data specifically for this purpose, we focus on English initially to identify the best filtering techniques and evaluation methods. We find that, when a large amount of data is available, selecting from the corpus based on criteria such as standard deviation of f0, fast speaking rate, and hypo-articulation produces the most intelligible voices.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- https://doi.org/10.21437/Interspeech.2020-2637
