ChivoxAI
sign in

/docs

en.sent.pron

Kernel Description

  • Support word-level superfluous reading, missed-reading, and wrong-reading detection;
  • Support the detection of stress, pause, rising and falling tone at the end of a sentence;
  • Adjust scoring tightness;
  • Support real-time feedback of words that have been spoken and evaluation scores;
  • Support specifying British or American pronunciation.

Request Parameters

Parameters Type Required Description
coreType String true "en.sent.pron" means Sentence Pronunciation Correction kernel.
accent int false Specify British or American pronunciation. 1, 2 or 3, Default value is 3.
  • 1. Accept British pronunciation.
  • 2: Accept American pronunciation.
  • 3: Accept both British and American pronunciation.
Now about 4000 words have been marked British and American pronunciation in our dictionary.
refText String true The English sentence you want to envalate the recording with.
We recommend sentence consisting of 2 to 20 words.Punctuation details reference see Text Symbol Description
rank int true Grading points system, fill in 100.
voiced int false Voiced switch, you can fill in 0 or 1, the default is 1.
0: The user's voiced and non-voiced pronunciation are both considered correct.
1: The user's pronunciation must be voiced to be correct.
attachAudioUrl number false Enable to return audio url or not.
  • 0: Disable
  • 1: Enable
result object false Results control parameters.
- details object false Detailed scoring options.
- - ext_cur_wrd number false Return the read content in real time. default 0.
0: Disable
1: Enable
- - gop_adjust number false Increase or reduce the evaluation scores.
The value range is between[-1,1] and the precision is 0.1 .
Default value is 0, which means using original scores.
If the value is between [0,1]. The larger the value is, the higher degree the score will be increased.
If the value is between [-1,0], the smaller the value is, the higher degree the scores will be reduced.
Stress, Rising tone, pause（optional）
  • Symbols can be used to make tone, stress tone, rising tone and pause in sentences.
  • Accents, ups and downs, and pauses are not counted in the total score.
Type Symbols Sample Description
Stress (s:1) Are(s:1) you ok? "Are" is maked with stressed.
Rising tone (t:1) Are you ok(t:1)? "Ok" is marked with rising tone.
Both Stress and rising tone (s:1,t:1) Are you ok(s:1,t:1)? Word “ok” is marked as both stress and rising tone, use commas to separate marks.
Pause (g:1) Are you(g:1) ok? Word “you” is marked with pause.

Sample Code

{
  "coreType": "en.sent.pron", 
  "refText": "I want to know the past of China.", 
  "accent": 1,
  "rank": 100, 
  "voiced":1,
  "attachAudioUrl": 1
  "result": {
    "details": {
	  "ext_cur_wrd": 1，
	  "gop_adjust":0.5
    }
  }
}

Real-time return result description

Key Type Description Recommendations
eof int Whether the final evaluation result
0: Indicates that the result is returned in real time during the recording process;
1: Indicates that the result is the final evaluation result after the recording is completed;		 Suggest to display
result object Return result description
- rec string During the evaluation process, the newly-recognized words will be returned to the read content in real time. Suggest to display
- phnspeed string Current speaking rate (unit: phoneme). For reference
- details object During the evaluation process, the score of each word of the read content is returned in real time.
- - text string Words that are read. Suggest to display
- - score number Read word score Suggest to display

Examples of real-time results

{
	"sdk": {
		"protocol": "websocket",
		"version": 16777216,
		"source": 4
	},
	"tokenId": "47e76381-****-****-****-********",
	"result": {
		"details": [
			{
				"text": "i",
				"score": 78
			}
		],
		"rec": "i",
		"phnspeed": 454
	},
	"eof": 0,
	"time": {
		"callback": "2020-12-04 16:51:22:870",
		"start": "2020-12-04 16:51:20:363",
		"connect": "2020-12-04 16:51:20:311"
	}
}

Example of final return result

  • The result is returned using the JSON structure, Example

Final return result description

Key Type Description Recommendations
uuid string Unique id of audio. Save uuid in database in case of need. For reference
audioUrl string Audio url.

Download audio in http protocol: Just add ".mp3" at the end of the URL.
Download audio in https protocol: Remove the port number, add ".mp3" at the end, and add "https://" to the prefix.
e.g.https://download.cloud.chivox.com/XXXXXXXX.mp3

Tips:
  • Chivox save audio for one week. Please save audio to your own server for long-term storage.
  • The domain name will be different for different access areas, and the actual return shall prevail.
 For reference
result object Scoring result
- wavetime number Audio duration(Unit: milliseconds) For reference
- overall number Overall score. The default percentage system. Suggest to display
- integrity number Score of integrity. Suggest to display
- accuracy number Score of accuracy(pronunciation evaluation of the read part). Suggest to display
- fluency object Fluency score details
- - pause number Number of pauses. Suggest to display
- - overall number Overall score of fluency. Suggest to display
- - speed number Speech rate, which is the number of words read per minute. Suggest to display
- details array Word-level superfluous reading, miss-reading, and wrong-reading detection and correction, and provide word-level scoring.
- - accent int 0, 1, 2 or 3:
  • 0: Its pronunciations are not marked with American or British accent.
  • 1: British pronunciation.
  • 2: American pronunciation.
  • 3: English pronunciation is the same as American pronunciation.
 Suggest to display
- - is_err number Pronunciation type.
0: correct.
1: superfluous reading.
2: missing reading.
3: misread.		 Suggest to display
- - lab string The word in the sentence.
For words that are read more, lab is marked as #.
For missed words, lab marks them as words in the reference text.
Words that are mispronounced, lab are marked as words in the reference text.		 Suggest to display
- - rec string Recognized words.
The missed word rec is marked as #.
Words that are read more, if the more read words are in refText, rec is marked as a more read word.
If the word is not in refText, rec field is marked as UNK.
The mispronounced word, if the mispronounced word is in refText, rec is marked as the mispronounced word.
The mispronounced word, if the mispronounced word is not in refText, rec is marked as UNK.		 Suggest to display
- - score number Word pronunciation score.
Words that are superfluous reading is scored as 0 if they are not in refText field(the rec field is marked as UNK).		 Suggest to display
- - start number The start time of the word in audio (Unit: milliseconds). For reference
- - end number The end time of the word in audio (Unit: milliseconds). For reference
- - stressref number 0 or 1:
0: Not marked to be stressed.
1: Marked to be stressed.		 Suggest to display
- - stressscore number 0 or 1:
0: Not stressed in audio.
1: Stressed in audio.
stressscore=stressref, indicating that the stress pronunciation is consistent with the mark.		 Suggest to display
- - toneref number 0 or 1:
0: Not marked to rising tone.
1: Marked to rising tone.		 Suggest to display
- - tonescore number 0 or 1:
0: Not reading with rising tone.
1: Reading with rising tone.
tonescore=toneref, indicating that the rising and falling tone is consistentwith the mark.		 Suggest to display
- - pause_ref number 0 or 1:
0: Not marked to pause.
1: Marked to pause.		 Suggest to display
- - pause_score number 0 or 1:
0: Reading without pause after the word.
1: Reading with pause after the word.
pause_score=pause_ref, indicating that the pause detection is consistent with the mark.		 Suggest to display
- - indict int The word's pronunciation is in dictionary or generated by the engine. 0, 1 or 2:
0: The word is not in Chivox’s dictionary and engine failed to generate its pronunciation.
1: The word is in Chivox’s dictionary.
2: The word is not in Chivox’s dictionary but the engine generates its pronunciation successfully.		 For reference
- - beginindex number The word first letter's index.
If the value is -1, it means that this is a multi-read word.
 Suggest to display
- - endindex number The word last letter's index.
If the value is -1, it means that this is a multi-read word.
 Suggest to display
- info object
- - tipId number Audio quality
For details, please refer to TipId field description		 For reference
- - tips string Error information

1. "post proc failed";
2. "fa decode failed!"
3. "empty or too short wav!"

These errors may be that the audio was not recorded successfully or the engine did not detect the user's valid voice, which can prompt the user to re-record.		 For reference

Note: The other returned parameters that are not shown above are internal ones, which you don't need to pay much atttention to.

SDK, API, MCP and Function Calling documentation on this site.