Intent Recognition and Unsupervised Slot Identification for Low Resourced Spoken Dialog Systems

Gupta, Abhinav; Deng, Olivia; Kushwaha, Akruti; Mittal, Shubham; Zeng, William J.; Rallabandi, Sai Krishna; Black, Alan W.

doi:10.48550/arxiv.2104.01287

Cited by 1 publication

(11 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…• Phone (E 1 ): Similar to the previous work [8], an embedding layer is learnt during the training step such that it maps the individual phones to a 256-dimensional features.…”

Section: Methodsmentioning

confidence: 99%

“…On the other hand, [6][7] [8] proposed to build NLU module using phones extracted from Allosaurus [9]. Allosaurus is a universal phone recognizer and therefore language independent.…”

Section: Related Workmentioning

confidence: 99%

“…[7] was the first extensive work on using phonetic transcriptions for intent classification on multiple low resourced lan- guages from two language families -Romance and Indic languages. [8] was the first study on building intent recognition systems for natural speech and achieved state-of-the-art results on Tamil. Yet their work was unable to achieve competitive results for languages like English or Sinhala with larger amounts of data.…”

Section: Related Workmentioning

confidence: 99%

“…Yet their work was unable to achieve competitive results for languages like English or Sinhala with larger amounts of data. Building on the work of [8], we propose to use Allosaurus to extract a sequence of dense representation instead of the sequence of discrete phones given an audio file as explained in Section 3. Using this, we are able to achieve close to perfect performance on English and significantly push the SOTA on Sinhala and Tamil.…”

Section: Related Workmentioning

confidence: 99%

“…Furthermore the authors also divide the dataset into train, development and, test sets such that there is no overlap of speakers between train and test. Similar to [8], we use the 31-class intent classification formulation of this dataset.…”

Section: Datasetmentioning

confidence: 99%

See 4 more Smart Citations

Intent Classification Using Pre-trained Language Agnostic Embeddings For Low Resource Languages

Yadav¹,

Gupta²,

Rallabandi³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Building Spoken Language Understanding (SLU) systems that do not rely on language specific Automatic Speech Recognition (ASR) is an important yet less explored problem in language processing. In this paper, we present a comparative study aimed at employing a pre-trained acoustic model to perform SLU in low resource scenarios. Specifically, we use three different embeddings extracted using Allosaurus, a pre-trained universal phone decoder: (1) Phone (2) Panphone, and (3) Allo embeddings. These embeddings are then used in identifying the spoken intent. We perform experiments across three different languages: English, Sinhala, and Tamil each with different data sizes to simulate high, medium, and low resource scenarios. Our system improves on the state-of-the-art (SOTA) intent classification accuracy by approximately 2.11% for Sinhala and 7.00% for Tamil and achieves competitive results on English. Furthermore, we present a quantitative analysis of how the performance scales with the number of training examples used per intent.

show abstract

“…• Phone (E 1 ): Similar to the previous work [8], an embedding layer is learnt during the training step such that it maps the individual phones to a 256-dimensional features.…”

Section: Methodsmentioning

confidence: 99%

“…On the other hand, [6][7] [8] proposed to build NLU module using phones extracted from Allosaurus [9]. Allosaurus is a universal phone recognizer and therefore language independent.…”

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Datasetmentioning

confidence: 99%

See 3 more Smart Citations