More Like this

1. EARSHOT: A Minimal Neural Network Model of Incremental Human Speech Recognition

   https://doi.org/10.1111/cogs.12823  

   Magnuson, James S. ; You, Heejo ; Luthra, Sahil ; Li, Monica ; Nam, Hosung ; Escabí, Monty ; Brown, Kevin ; Allopenna, Paul D. ; Theodore, Rachel M. ; Monto, Nicholas ; et al ( April 2020 , Cognitive Science)

   Despite thelack of invariance problem(the many‐to‐many mapping between acoustics and percepts), human listeners experience phonetic constancy and typically perceive what a speaker intends. Most models of human speech recognition (HSR) have side‐stepped this problem, working with abstract, idealized inputs and deferring the challenge of working with real speech. In contrast, carefully engineered deep learning networks allow robust, real‐world automatic speech recognition (ASR). However, the complexities of deep learning architectures and training regimens make it difficult to use them to provide direct insights into mechanisms that may support HSR. In this brief article, we report preliminary results from a two‐layer network that borrows one element from ASR,long short‐term memorynodes, which provide dynamic memory for a range of temporal spans. This allows the model to learn to map real speech from multiple talkers to semantic targets with high accuracy, with human‐like timecourse of lexical access and phonological competition. Internal representations emerge that resemble phonetically organized responses in human superior temporal gyrus, suggesting that the model develops a distributed phonological code despite no explicit training on phonetic or phonemic targets. The ability to work with real speech is a major advance for cognitive models of HSR.

    

   more » « less
2. An Efficient Temporal Modeling Approach for Speech Emotion Recognition by Mapping Varied Duration Sentences into Fixed Number of Chunks

   https://doi.org/10.21437/Interspeech.2020-2636  

   Lin, Wei-Cheng ; Busso, Carlos ( October 2020 , Interspeech 2020)

   null (Ed.)

   Speech emotion recognition (SER) plays an important role in multiple fields such as healthcare, human-computer interaction (HCI), and security and defense. Emotional labels are often annotated at the sentence-level (i.e., one label per sentence), resulting in a sequence-to-one recognition problem. Traditionally, studies have relied on statistical descriptions, which are com- puted over time from low level descriptors (LLDs), creating a fixed dimension sentence-level feature representation regardless of the duration of the sentence. However sentence-level features lack temporal information, which limits the performance of SER systems. Recently, new deep learning architectures have been proposed to model temporal data. An important question is how to extract emotion-relevant features with temporal infor- mation. This study proposes a novel data processing approach that extracts a fixed number of small chunks over sentences of different durations by changing the overlap between these chunks. The approach is flexible, providing an ideal frame- work to combine gated network or attention mechanisms with long short-term memory (LSTM) networks. Our experimental results based on the MSP-Podcast dataset demonstrate that the proposed method not only significantly improves recognition accuracy over alternative temporal-based models relying on LSTM, but also leads to computational efficiency. 

   more » « less
3. Assessment of Non-Native Speech Intelligibility using Wav2vec2-based Mispronunciation Detection and Multi-level Goodness of Pronunciation Transformer

   https://doi.org/10.21437/Interspeech.2023-2371  

   Shekar, Ram C. ; Yang, Mu ; Hirschi, Kevin ; Looney, Stephen ; Kang, Okim ; Hansen, John H. ( August 2023 , ISCA INTERSPEECH-2023)

   N/A (Ed.)

   Automatic pronunciation assessment (APA) plays an important role in providing feedback for self-directed language learners in computer-assisted pronunciation training (CAPT). Several mispronunciation detection and diagnosis (MDD) systems have achieved promising performance based on end-to-end phoneme recognition. However, assessing the intelligibility of second language (L2) remains a challenging problem. One issue is the lack of large-scale labeled speech data from non-native speakers. Additionally, relying only on one aspect (e.g., accuracy) at a phonetic level may not provide a sufficient assessment of pronunciation quality and L2 intelligibility. It is possible to leverage segmental/phonetic-level features such as goodness of pronunciation (GOP), however, feature granularity may cause a discrepancy in prosodic-level (suprasegmental) pronunciation assessment. In this study, Wav2vec 2.0-based MDD and Goodness Of Pronunciation feature-based Transformer are employed to characterize L2 intelligibility. Here, an L2 speech dataset, with human-annotated prosodic (suprasegmental) labels, is used for multi-granular and multi-aspect pronunciation assessment and identification of factors important for intelligibility in L2 English speech. The study provides a transformative comparative assessment of automated pronunciation scores versus the relationship between suprasegmental features and listener perceptions, which taken collectively can help support the development of instantaneous assessment tools and solutions for L2 learners. 

   more » « less
4. Neural network vs. HMM speech recognition systems as models of human cross-linguistic phonetic perception

   Schatz, Thomas ; Feldman, Naomi H. ( September 2018 , Proceedings of the Conference on Cognitive Computational Neuroscience)

   The way listeners perceive speech sounds is largely determined by the language(s) they were exposed to as a child. For example, native speakers of Japanese have a hard time discriminating between American English /ɹ/ and /l/, a phonetic contrast that has no equivalent in Japanese. Such effects are typically attributed to knowledge of sounds in the native language, but quantitative models of how these effects arise from linguistic knowledge are lacking. One possible source for such models is Automatic Speech Recognition (ASR) technology. We implement models based on two types of systems from the ASR literature—hidden Markov models (HMMs) and the more recent, and more accurate, neural network systems—and ask whether, in addition to showing better performance, the neural network systems also provide better models of human perception. We find that while both types of systems can account for Japanese natives’ difficulty with American English /ɹ/ and /l/, only the neural network system successfully accounts for Japanese natives’ facility with Japanese vowel length contrasts. Our work provides a new example, in the domain of speech perception, of an often observed correlation between task performance and similarity to human behavior. 

   more » « less
5. Domain Expansion for End-to-End Speech Recognition: Applications for Accent/Dialect Speech

   https://doi.org/10.1109/TASLP.2022.3233238  

   Ghorbani, Shahram ; Hansen, John H.L. ( January 2023 , IEEE/ACM Transactions on Audio, Speech, and Language Processing)

   Training Automatic Speech Recognition (ASR) systems with sequentially incoming data from alternate domains is an essential milestone in order to reach human intelligibility level in speech recognition. The main challenge of sequential learning is that current adaptation techniques result in significant performance degradation for previously-seen domains.To mitigate the catastrophic forgetting problem, this study proposes effective domain expansion techniques for two scenarios: 1)where only new domain data is available, and 2) where both prior and new domain data are available. We examine the efficacy of the approaches through experiments on adapting a model trained with native English to different English accents. For the first scenario, we study several existing and proposed regularization-based approaches to mitigate performance loss of initial data.The experiments demonstrate the superior performanceo four proposed Soft KL-Divergence(SKLD)-Model Averaging (MA) approach. In this approach, SKLD first alleviates the forgetting problem during adaptation; next, MA makes the final efficient compromise between the two domains by averaging parameters of the initial and adapted models. For the second scenario, we explore several rehearsal-based approaches, which leverage initial data to maintain the original model performance.We propose Gradient Averaging (GA) as well as an approach which operates by averaging gradients computed for both initial and new domains. Experiments demonstrate that GA outperforms retraining and specifically designed continual learning approaches, such as Averaged Gradient Episodic Memory (AGEM). Moreover, GA significantly improves computational costs over the complete retraining approach. 

   more » « less