Spontaneous Speech Assessment with SpeechSuper's API: Enhancing Language Testing


Conversations are an essential part of our daily lives. In academic settings, speaking is necessary to express opinions and collaborate with peers. However, natural conversations are unscripted, making the evaluation of spontaneous speech a significant challenge. 


High-stakes English-level tests such as IELTS and TOEFL evaluate spontaneous speech based on multiple aspects, including vocabulary, grammar, pronunciation, fluency, and topic development. However, accurately and automatically assessing these aspects of spoken language presents a significant challenge. At SpeechSuper, we have taken on this challenge with the aim of developing precise and efficient evaluation methods.


Drawing primarily from the evaluation rubrics used for IELTS speaking assessments, SpeechSuper's spontaneous speech assessment API will provide comprehensive scores for both overall performance and the 5 sub-dimensions mentioned above. In addition, our API will offer detailed analytics to help users better interpret and understand their scores.


SpeechSuper spontaneous speech assessment API can provide:


  • Overall speaking score (IELTS estimate)
  • Pronunciation score (IELTS estimate), including scores for sentences and words
  • Lexical resource score (IELTS estimate)
  • Fluency and coherence score (IELTS estimate), along with technical details such as speaking speed, long pause count, and filler word count
  • Grammatical range & accuracy score (IELTS estimate), with detailed analysis of grammatical errors and correction suggestions for sentences
  • Topic Development score, a percentage that shows how well the response stayed on topic
  • Transcript of the user's response

SpeechSuper's spontaneous speech assessment API outline


With SpeechSuper's spontaneous speech assessment API, you can gain valuable insights into users' speaking abilities. Stay tuned!


Written by Qiusi and ChatGPT

----------------------------------------------------------


ABOUT US


Qiusi is a product manager in China’s EdTech industry focusing on language learning and AI. She enjoys writing stories. You can reach her at qiusi.dong@speechsuper.com


SpeechSuper provides cutting-edge AI speech assessment (a.k.a pronunciation assessment or pronunciation score) APIs for language learning products. Comprehensive feedback covers pronunciation score, fluency, completeness, rhythm, stress, liaison, etc. Languages supported include English, Mandarin Chinese, French, German, Korean, Japanese, Russian, Spanish, and more.


*Prior written consent is needed for any form of republication, modification, repost, or distribution of the contents.

Comments

Post a Comment

Popular posts from this blog

How Accurate is Pronunciation Assessment?

Image
Pronunciation assessment APIs usually offer pronunciation scores at phoneme level, syllable level, word level, and sentence level. Yet, how do you know if the scores are accurate? By comparing the predicted pronunciation scores of the testset with the golden standard (human label). The closer the two results, the more accurate the algorithm is.  To make the metric(s) representative and useful, we need to think carefully about 1) testset, and 2) performance metrics. Testset The testset is usually designed by an AI product manager. He/She should ensure that the testset can 1) reflect real user scenarios, 2) have good data variety, and 3) cover a wide range of use cases. For example, SpeechSuper's API testsets consist of masked audios from language learners sampled from our real user base. They usually cover a wide spectrum of phonetic combinations in a specific language. The testsets not only contain data recorded in a quiet environment but also with background noise. Metrics I guess...
Read more

SpeechSuper English Speech to Text API Supports Inverse Text Normalization

Image
SpeechSuper released a new speech-to-text (speech recognition) API feature: inverse text normalization. What is inverse text normalization? It converts the words to numerical or scientific expressions for better readability and understanding. For example, the recognized words 'seventeen dollars' can be converted to '$17' via inverse text normalization. We now support inverse text normalization in the following domains. 1. Cardinal number and currency   SpeechSuper's English speech-to-text API can support number and currency conversion. For example, if the recognized words are 'It costs three hundred and one dollars.', it will be converted to 'It costs $301.' 2. Date SpeechSuper's English speech-to-text API can support date conversion. For example, if the recognized words are 'I was born on November first nineteen ninety-seven.', it will be converted to 'I was born on November 1, 1997'. 3. Decimal number SpeechSuper's English s...
Read more

Enhanced Indian English Pronunciation Assessment Available on SpeechSuper API

Image
Introducing SpeechSuper's latest release: the   Indian English   pronunciation assessment API! Now, you can leverage this powerful tool to assess English word, phrase/sentence, and paragraph pronunciation specifically in the Indian English dialect. Click to experience the demo firsthand. With our API, Indian professionals proficient in English can achieve higher scores while embracing their unique accents. As long as an accent doesn't hinder understanding, it adds to the richness of communication. To make use of this cutting-edge feature, include the following line in your request parameters for English word, sentence, and paragraph pronunciation assessment API, and you're good to go: "accent_dialect": "indian" If you're eager to explore this feature and would like to experience a free trial, simply visit our  website , click the "Contact us" button, and fill out the form. Once submitted, I will promptly reach out to provide you with the fr...
Read more