More Like this

1. That Sounds Familiar: An Analysis of Phonetic Representations Transfer Across Languages

   https://doi.org/10.21437/Interspeech.2020-2513  

   Żelasko, Piotr; Moro-Velázquez, Laureano; Hasegawa-Johnson, Mark; Scharenborg, Odette; Dehak, Najim (October 2020, Interspeech)

   null (Ed.)

   Only a handful of the world’s languages are abundant with the resources that enable practical applications of speech processing technologies. One of the methods to overcome this problem is to use the resources existing in other languages to train a mul-tilingual automatic speech recognition (ASR) model, which, intuitively, should learn some universal phonetic representations.In this work, we focus on gaining a deeper understanding ofhow general these representations might be, and how individual phones are getting improved in a multilingual setting. To that end, we select a phonetically diverse set of languages, and perform a series of monolingual, multilingual and crosslingual (zero-shot) experiments. The ASR is trained to recognize the International Phonetic Alphabet (IPA) token sequences. We ob-serve significant improvements across all languages in the multilingual setting, and stark degradation in the crosslingual setting, where the model, among other errors, considers Javanese as a tone language. Notably, as little as 10 hours of the target language training data tremendously reduces ASR error rates.Our analysis uncovered that even the phones that are unique to a single language can benefit greatly from adding training data from other languages - an encouraging result for the low-resource speech community 

   more » « less
2. Capturing Formality in Speech Across Domains and Languages

   https://doi.org/10.21437/Interspeech.2023-1852  

   Bhattacharya, Debasmita; Chi, Jie; Hirschberg, Julia; Bell, Peter (August 2023, Interspeech 2023)

   The linguistic notion of formality is one dimension of stylistic variation in human communication. A universal characteristic of language production, formality has surface-level realizations in written and spoken language. In this work, we explore ways of measuring the formality of such realizations in multilingual speech corpora across a wide range of domains. We compare measures of formality, contrasting textual and acoustic-prosodic metrics. We believe that a combination of these should correlate well with downstream applications. Our findings include: an indication that certain prosodic variables might play a stronger role than others; no correlation between prosodic and textual measures; limited evidence for anticipated inter-domain trends, but some evidence of consistency of measures between languages. We conclude that non-lexical indicators of formality in speech may be more subtle than our initial expectations, motivating further work on reliably encoding spoken formality. 

   more » « less
3. Learning to Scale Multilingual Representations for Vision-Language Tasks

   Andrea Burns, Donghyun Kim (January 2020, European Conference on Computer Vision)

   null (Ed.)

   Current multilingual vision-language models either require a large number of additional parameters for each supported language, or suffer performance degradation as languages are added. In this paper, we-9*6 propose a Scalable Multilingual Aligned Language Representation (SMALR) that supports many languages with few model parameters without sacrificing downstream task performance. SMALR learns a fixed size language-agnostic representation for most words in a multilingual vocabulary, keeping language-specific features for just a few. We use a masked cross-language modeling loss to align features with context from other languages. Additionally, we propose a cross-lingual consistency module that ensures predictions made for a query and its machine translation are comparable. The effectiveness of SMALR is demonstrated with ten diverse languages, over twice the number supported in vision-language tasks to date. We evaluate on multilingual image-sentence retrieval and outperform prior work by 3–4% with less than 1/5th the training parameters compared to other word embedding methods. 

   more » « less
4. Learning to Scale Multilingual Representations for Vision-Language Tasks

   https://doi.org/10.1007/978-3-030-58548-8  

   Andrea Burns, Donghyun Kim (January 2020, European Conference on Computer Vision)

   null (Ed.)

   Current multilingual vision-language models either require a large number of additional parameters for each supported language, or suffer performance degradation as languages are added. In this paper, we-9*6 propose a Scalable Multilingual Aligned Language Representation (SMALR) that supports many languages with few model parameters without sacrificing downstream task performance. SMALR learns a fixed size language-agnostic representation for most words in a multilingual vocabulary, keeping language-specific features for just a few. We use a masked cross-language modeling loss to align features with context from other languages. Additionally, we propose a cross-lingual consistency module that ensures predictions made for a query and its machine translation are comparable. The effectiveness of SMALR is demonstrated with ten diverse languages, over twice the number supported in vision-language tasks to date. We evaluate on multilingual image-sentence retrieval and outperform prior work by 3–4% with less than 1/5th the training parameters compared to other word embedding methods. 

   more » « less
5. How Phonotactics Affect Multilingual and Zero-Shot ASR Performance

   https://doi.org/10.1109/ICASSP39728.2021.9414478  

   Feng, Siyuan; Zelasko, Piotr; Moro-Velazquez, Laureano; Abavisani, Ali; Hasegawa-Johnson, Mark; Scharenborg, Odette; Dehak, Najim (June 2021, ICASSP)

   null (Ed.)

   The idea of combining multiple languages’ recordings to train a single automatic speech recognition (ASR) model brings the promise of the emergence of universal speech representation. Recently, a Transformer encoder-decoder model has been shown to leverage multilingual data well in IPA transcriptions of languages presented during training. However, the representations it learned were not successful in zero-shot transfer to unseen languages. Because that model lacks an explicit factorization of the acoustic model (AM) and language model (LM), it is unclear to what degree the performance suffered from differences in pronunciation or the mismatch in phonotactics. To gain more insight into the factors limiting zero-shot ASR transfer, we replace the encoder-decoder with a hybrid ASR system consisting of a separate AM and LM. Then, we perform an extensive evaluation of monolingual, multilingual, and crosslingual (zero-shot) acoustic and language models on a set of 13 phonetically diverse languages. We show that the gain from modeling crosslingual phonotactics is limited, and imposing a too strong model can hurt the zero-shot transfer. Furthermore, we find that a multilingual LM hurts a multilingual ASR system’s performance, and retaining only the target language’s phonotactic data in LM training is preferable. 

   more » « less