More Like this

1. Confirming the Generalizability of a Chain-Based Animacy Detector

   Jahan, Labiba; Yarlott, W. Victor; Rahul, Mittal; Finlayson, Mark A. (January 2021, 1st Workshop on Artificial Intelligence for Narratives (AI4N 2020))

   null (Ed.)

   Animacy is the characteristic of a referent beingable to independently carry out actions in a storyworld (e.g., movement, communication). It is anecessary property of characters in stories, and sodetecting animacy is an important step in automaticstory understanding; it is also potentially useful formany other natural language processing tasks suchas word sense disambiguation, coreference resolu-tion, character identification, and semantic role la-beling. Recent work by Jahanet al.[2018]demon-strated a new approach to detecting animacy whereanimacy is considered a direct property of corefer-ence chains (and referring expressions) rather thanwords. In Jahanet al., they combined hand-builtrules and machine learning (ML) to identify the an-imacy of referring expressions and used majorityvoting to assign the animacy of coreference chains,and reported high performance of up to 0.90F1. Inthis short report we verify that the approach gener-alizes to two different corpora (OntoNotes and theCorpus of English Novels) and we confirmed thatthe hybrid model performs best, with the rule-basedmodel in second place. Our tests apply the animacyclassifier to almost twice as much data as Jahanetal.’s initial study. Our results also strongly suggest,as would be expected, the dependence of the mod-els on coreference chain quality. We release ourdata and code to enable reproducibility. 

   more » « less
2. Lexico-syntactic constraints influence verbal working memory in sentence-like lists

   https://doi.org/10.3758/s13421-023-01496-2  

   Schwering, Steven C.; Jacobs, Cassandra L.; Montemayor, Janelle; MacDonald, Maryellen C. (December 2023, Memory & Cognition)

   We test predictions from the language emergent perspective on verbal working memory that lexico-syntactic constraints should support both item and order memory. In natural language, long-term knowledge of lexico-syntactic patterns involving part of speech, verb biases, and noun animacy support language comprehension and production. In three experiments, participants were presented with randomly generated dative-like sentences or lists in which part of speech, verb biases, and animacy of a single word were manipulated. Participants were more likely to recall words in the correct position when presented with a verb over a noun in the verb position, a good dative verb over an intransitive verb in the verb position, and an animate noun over an inanimate noun in the subject noun position. These results demonstrate that interactions between words and their context in the form of lexico-syntactic constraints influence verbal working memory. 

   more » « less
3. Teacher-Student learning based Acoustic Models for Robust Speech Recognition in Naturalistic Childhood Classroom settings

   Kothalkar, P.V. (February 2023, Speech communication)

   Speech and language development are early indicators of overall analytical and learning ability in children. The preschool classroom is a rich language environment for monitoring and ensuring growth in young children by measuring their vocal interactions with both teachers and classmates. Early childhood researchers recognize the importance in analyzing naturalistic vs. controlled lab recordings to measure both quality and quantity of child interactions. Recently, large language model-based speech technologies have performed well on conversational speech recognition. In this regard, we assess performance of such models on the wide dynamic scenario of early childhood classroom settings. This study investigates an alternate Deep Learning-based Teacher-Student learning solution for recognizing adult speech within preschool interactions. Our proposed adapted model achieves the best F1-score for recognizing most frequent 400 words on test sets for both classrooms. Additionally, F1-scores for alternate word groups provides a breakdown of performance across relevant language-based word-categories. The study demonstrates the prospects of addressing educational assessment needs through communication audio stream analysis, while maintaining both security and privacy of all children and adults. The resulting child communication metrics from this study can also be used for broad-based feedback for teachers. 

   more » « less
4. Self-supervised Semantic-driven Phoneme Discovery for Zero-resource Speech Recognition

   https://doi.org/10.18653/v1/2022.acl-long.553  

   Wang, Liming; Feng, Siyuan; Hasegawa-Johnson, Mark; Yoo, Chang (January 2022, Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers))

   Muresan, Smaranda; Nakov, Preslav; Villavicencio, Aline (Ed.)

   Phonemes are defined by their relationship to words: changing a phoneme changes the word. Learning a phoneme inventory with little supervision has been a longstanding challenge with important applications to under-resourced speech technology. In this paper, we bridge the gap between the linguistic and statistical definition of phonemes and propose a novel neural discrete representation learning model for self-supervised learning of phoneme inventory with raw speech and word labels. Under mild assumptions, we prove that the phoneme inventory learned by our approach converges to the true one with an exponentially low error rate. Moreover, in experiments on TIMIT and Mboshi benchmarks, our approach consistently learns a better phoneme-level representation and achieves a lower error rate in a zero-resource phoneme recognition task than previous state-of-the-art self-supervised representation learning algorithms. 

   more » « less
5. SyllableLM: Learning Coarse Semantic Units for Speech Language Models

   Baade, A; Peng, P; Harwath, D (October 2024, https://doi.org/10.48550/arXiv.2410.04029)

   Language models require tokenized inputs. However, tokenization strategies for continuous data like audio and vision are often based on simple heuristics such as fixed sized convolutions or discrete clustering, which do not necessarily align with the semantic structure of the data. For speech in particular, the high resolution of waveforms (16,000 samples/second or more) presents a significant challenge as speech-based language models have had to use several times more tokens per word than text-based language models. In this work, we introduce a controllable self-supervised technique to merge speech representations into coarser syllable-like units while still preserving semantic information. We do this by 1) extracting noisy boundaries through analyzing correlations in pretrained encoder losses and 2) iteratively improving model representations with a novel distillation technique. Our method produces controllable-rate semantic units at as low as 5Hz and 60bps and achieves SotA in syllabic segmentation and clustering. Using these coarse tokens, we successfully train SyllableLM, a Speech Language Model (SpeechLM) that matches or outperforms current SotA SpeechLMs on a range of spoken language modeling tasks. SyllableLM also achieves significant improvements in efficiency with a 30x reduction in training compute and a 4x wall-clock inference speedup. 

   more » « less