What is Speech Assessment and Why it Matters

by Qiusi, Product Manager of SpeechSuper 

What is Speech Assessment

Speech assessment is the process of giving algorithm-based corrective feedback for speaking activities in language learning. It's also sometimes called pronunciation assessment.


  • Speech Assessment 101

Speech assessment is largely based on the "Goodness of Pronunciation" (GoP) algorithm developed over 20 years. While automatic speech recognition (ASR) aims to decode the best possible option of acoustic model and language model combined derived from data in a specified language, GoP only cares about the acoustic model with the language model pre-defined, hence producing an acoustic likeliness score measuring “how similar a speech sounds like compared to native speakers of a particular language”, which, in short, is pronunciation.


Simply put, for speech assessment, the input is speech audio + reference text, and the output is a score of pronunciation.  


  • Evolution of Speech Assessment

Over the past decades, the GoP algorithm has been evolving, having more features under the belt. Meanwhile, the acoustic model gains tremendous development thanks to deep learning techniques. It now supports speech assessment of various granularities, from phone, syllable, to sentence and paragraph. The feedback consists of plenty of segmental and suprasegmental aspects of speech production, for instance, phoneme mispronunciation, fluency, pause, rhythm, tone, linking, etc. Given massive training data, we could also assess various language aspects like vocabulary, grammatical errors, cohesion, coherence, relevance, etc. Almost all linguistic aspects that you can imagine could be analyzed from a continuous speech.  


Why it Matters


  • Language learning is ineffective without speaking activities.

Sufficient speaking activities are crucial in language learning. 

As an introverted English learner myself since 5 years old, I sincerely hoped that today's various speaking activities in language learning apps could help me out back in my childhood because I felt awkward speaking and practicing English in front of people. Without enough speaking practice in my critical period, speaking is the weakest among my four foundation language skills.


  • Language learners learn from feedback.

Speech assessment offers an eclectic range of feedback that language learners can learn from. 


Learners may be negatively influenced by their native language when learning a new language. Feedback is highly useful. I'm a native speaker of Mandarin Chinese, a syllable-timed language. English is my L2 language, a stress-timed one. Hence, I had a hard time laying stress within words and between words in reading aloud activities. With proper stress feedback, I corrected myself gradually to a proper rhythm. Stress detection is a feature that SpeechSuper APIs offer. Try our demo here. 



  • Speech assessment improves conversion and retention.

Successful language learning services leverage speaking assessment to engage users and stand out from competitors, like Rosetta Stone, Elsa, Duolingo, and so on. 

According to Elsa, with speaking activities and feedback, the conversion rate from free users to paid users would be 3 times as before. Besides, the user engagement will boost to 8 times with the average user session time being 23 minutes.  


Conclusion

Speaking activities are crucial and speaking assessment holds its value in the global trend of online learning. 

We think that the appropriate and wise use of speech assessment is still in its infancy. We are endeavoring to make more advances in speech assessment and looking forward to landing those progress to solve real problems in the realm of language learning.


At  SpeechSuper, we develop AI-based speech technologies to analyze speech from language learners, including pronunciation, fluency, completeness, and more. If you’re interested, please contact us on the website.


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

DON’T Use Speech Recognition in Language Learning Apps

Image
After researching ~100 language learning apps in South East Asia and the American app market, I found that only 27% allow users to practice speaking, and most of them use speech recognition as speaking feedback.  Using speech recognition is ineffective in language learning for two reasons. 1. Good pronunciations are all alike; every mispronunciation is faulty in its own way. One of the barriers to language learning is the mother tongue, especially for learners 12 years old and above. Deeply influenced by the sound system of their mother tongues, language learners may confuse sounds in their mother tongue with those in a new language. There are over 7000 languages globally, so a single language corresponds to a broad spectrum of mispronunciations from language learners.  It is happy if a recognition system can recognize speech, but what matters the most is how to deal with mispronunciations, which fail the recognition system. It can not shed light on where and how to improve, but those
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