SmarTerp: A CAI System to Support Simultaneous Interpreters in Real-Time

no code implementations • TRITON 2021 • Susana Rodriguez, Roberto Gretter, Marco Matassoni, Alvaro Alonso, Oscar Corcho, Mariano Rico, Falavigna Daniele

We present a system to support simultaneous interpreting in specific domains.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +4

Seed Words Based Data Selection for Language Model Adaptation

no code implementations • MTSummit 2021 • Roberto Gretter, Marco Matassoni, Daniele Falavigna

We address the problem of language model customization in applications where the ASR component needs to manage domain-specific terminology; although current state-of-the-art speech recognition technology provides excellent results for generic domains, the adaptation to specialized dictionaries or glossaries is still an open issue.

Language Modelling Semantic Similarity +3

Mixtures of Deep Neural Experts for Automated Speech Scoring

no code implementations • 23 Jun 2021 • Sara Papi, Edmondo Trentin, Roberto Gretter, Marco Matassoni, Daniele Falavigna

The paper copes with the task of automatic assessment of second language proficiency from the language learners' spoken responses to test prompts.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +2

Experiments of ASR-based mispronunciation detection for children and adult English learners

no code implementations • 13 Apr 2021 • Nina Hosseini-Kivanani, Roberto Gretter, Marco Matassoni, Giuseppe Daniele Falavigna

In this study, we develop a mispronunciation assessment system that checks the pronunciation of non-native English speakers, identifies the commonly mispronounced phonemes of Italian learners of English, and presents an evaluation of the non-native pronunciation observed in phonetically annotated speech corpora.

Language Modelling speech-recognition +1

Automatically Assess Children's Reading Skills

no code implementations • LREC 2020 • Ornella Mich, Nadia Mana, Roberto Gretter, Marco Matassoni, Daniele Falavigna

Our system, based on ASR technology, implements the Cornoldi{'}s MT battery, which is a well-known Italian test to assess reading skills.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +1

TLT-school: a Corpus of Non Native Children Speech

no code implementations • LREC 2020 • Roberto Gretter, Marco Matassoni, Stefano Bannò, Daniele Falavigna

This paper describes "TLT-school" a corpus of speech utterances collected in schools of northern Italy for assessing the performance of students learning both English and German.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +1

Automatic assessment of spoken language proficiency of non-native children

no code implementations • 15 Mar 2019 • Roberto Gretter, Katharina Allgaier, Svetlana Tchistiakova, Daniele Falavigna

This paper describes technology developed to automatically grade Italian students (ages 9-16) on their English and German spoken language proficiency.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +1

Non-native children speech recognition through transfer learning

no code implementations • 25 Sep 2018 • Marco Matassoni, Roberto Gretter, Daniele Falavigna, Diego Giuliani

This work deals with non-native children's speech and investigates both multi-task and transfer learning approaches to adapt a multi-language Deep Neural Network (DNN) to speakers, specifically children, learning a foreign language.

speech-recognition Speech Recognition +1

Euronews: a multilingual speech corpus for ASR

no code implementations • LREC 2014 • Roberto Gretter

In this paper we present a multilingual speech corpus, designed for Automatic Speech Recognition (ASR) purposes.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +2