Questions tagged [speech-recognition]

Software that can recognize spoken words as an input, typically to convert it into text form (speech-to-text). Use [voice-recognition] for software that can recognize/identify the speaker.

43 questions with no upvoted or accepted answers
Filter by
Sorted by
Tagged with
7 votes
0 answers
2k views

Adding closed captions to online videos

I am looking for a program/browser extension that can generate closed captions on any video I watch online. I like to watch a lot of YouTube tutorials, breaking news, and general information videos ...
user avatar
6 votes
0 answers
486 views

Open source library/API to validate word pronunciation (like in Rosetta Stone)

I'm planning to make a web app that captures the user speech and tell the user if he/she is spelling the words in the right way, and gave him/her hits as to where he needs to improve his spelling. To ...
  • 61
6 votes
0 answers
4k views

Lyrics extractor (speech recognition) from a song

I have some songs in English that do not have published lyrics due to those are not popular. So I'm looking for an online service or a standalone app that can extract (recognize) lyrics (as text) from ...
6 votes
0 answers
55 views

Audio recorder and translator program?

I am currently looking for a program for Windows 7 that records or listens to audio or human speech in another language, E.g. Japanese and then translates it into English. I need a program that is ...
6 votes
0 answers
82 views

Voice commanding a web browser on GNU/Linux

I’d like to browse the Web by using voice commands. It must be possible to scroll the page and to focus and click at links, and it should be possible to fill in and submit forms. It must be FLOSS (...
  • 7,780
5 votes
0 answers
37 views

Phone app for spoken definitions while reading

When I read on my Kindle, I can simply highlight a word to get its definition. When I read a paper book, this doesn't work. I'm looking for an app on my phone that allows the following: (1) I ask it ...
  • 151
4 votes
0 answers
26 views

Language recognizer (from a sound tell whether French/Romanian/Korean/etc)

I want an Android app that can listen to someone speaking and tell what language it is. Example: Sound "The Maharashtra government has given a 90-day period for manufacturers to dispose of existing ...
  • 18.9k
4 votes
0 answers
39 views

App that automatically records/recognizes speech and compiles in a list?

I'm a business owner and am constantly pulled in different directions. To keep track of what I do all day, I use a system where I use DROPVOX to record what I am doing, and a virtual assistant to ...
user avatar
4 votes
0 answers
226 views

Android audio recorder with speech recognition

I'm looking for an audio recorder that can perform speech recognition while it is recording (but would also keep the audio recording) so that afterwards I could easily browse the recordings along with ...
  • 295
4 votes
0 answers
48 views

Special education AI assistant

I saw a video of a robot used in special education with children on the autism spectrum (https://www.youtube.com/watch?v=FQcjfebQXgQ). My son isn't autistic, he has Tourette Syndrome, ADHD, executive ...
3 votes
0 answers
49 views

Open source English dictation software for Ubuntu

I need an open source software (speech to text) that can write plain English from my dictation in Ubuntu.
  • 181
3 votes
1 answer
172 views

Transcriber software for Windows?

Suppose that I am watching some educational movies. for example a course on a university that has been published on the web and I want to write a pamphlet for my self. Since I'm not in the classroom ...
3 votes
0 answers
784 views

Offline voice typing alternative for Android?

I would like an alternative to the voice search application provided by Google's Voice Typing. This is because Voice Typing puts out an annoying 'ding' sound when it starts recording/interpreting, ...
  • 279
3 votes
0 answers
46 views

Android app for feedback on plosives and sibilance?

My girlfriend's son is speech delayed, and has problems pronouncing 'b's, 'p's, and 's'es. Is there an Android app that will give some feedback based on plosives or sibilance sound? I think getting ...
3 votes
0 answers
67 views

Is there a software that provides access to google speech-to-text on a PC desktop?

Google has speech to text in the google search page, but is it possible to access the same API/functionality for general purpose speech to text conversion on the windows PC, outside of the browser?
  • 385
2 votes
0 answers
32 views

Self hosted speech to text software on linux with gui?

I want to make it so the hours and hours of notes to self I have can be turned into easily searchable text without sending them off to some third party to be processed. Should work on an offline ...
2 votes
0 answers
48 views

we want to redact / mast part of an audio file where the audio has some sensitive information. Is there any module in python to achieve this?

We receive multiple audio files every day and it will have sensitive information. We need to mask this information but retain rest of the audio. The way I see it we need to perform below steps first ...
  • 21
2 votes
0 answers
45 views

Easy Speech to Text Software?

I would like to create an AI helper for my computer, kind of like Cortana. I have made attempts at this in the past, but those projects drifted away, and were replace by higher priorities, so I'm ...
2 votes
0 answers
559 views

Speech recognition for Korean language on Microsoft Windows

I am looking for a speech recognition program for the Korean language on Microsoft Windows 7. As far as I know: Dragon NaturallySpeaking 12 and 13 does not support Korean Microsoft speech ...
2 votes
0 answers
44 views

Video player with caption automatically generated from the audio

I'm looking for a audio/video player with caption automatically generated from the audio track (speech to text). The speech recognition doesn't need to be perfect, I want it so I can skip the boring ...
  • 123
2 votes
0 answers
37 views

What are some good commercially available services that can do forced alignment of a corrected transcript?

I am looking for commercial solutions for automatically allocating time stamps for a the captions in a transcript. The service should take the transcript (sans the time stamps) and the corresponding ...
2 votes
1 answer
112 views

Automatic subtitle syncronization

I have subtitles without timing and I need to automatically sync them to a video. After some searching, I found http://www.jaivox.com/wordalign.html http://cmusphinx.sourceforge.net/2014/07/long-...
  • 300
2 votes
0 answers
48 views

Speech-to-text / Translation app recommendations?

Are there any good (preferably Windows or Android) apps that will do speech-to-text and also translate the text from English to Spanish or from Spanish to English. I know they would not be perfect, ...
2 votes
0 answers
27 views

Program to quantify precisely how much lag Dragon NaturallySpeaking has

I am looking for a tool to quantify precisely how much recognition lag Dragon NaturallySpeaking has. The recognition lag is the time it takes for Dragon NaturallySpeaking to transcribe what the user ...
1 vote
1 answer
30 views

Speech software for Windows

I'm looking for some software that would allow me to convert my voice into text. This would really help because it hurts my hands to type. I would like to be able to open applications, my web browser, ...
  • 11
1 vote
0 answers
20 views

Creating time marks for speech audio with existing text

My case: I have audio of speech and already prepared text of same speech. And I need add time marks for text, so I can move between audio parts with help of text hints. As I can see Google's Speech-to-...
  • 143
1 vote
0 answers
10 views

Video frame lookup or search using verbal audio utterances

I'm an animator trying to get a program that will use machine learning to automate the lip syncing process. The program I need made will have two files given to it: a seed, and an audio file. The seed ...
  • 111
1 vote
1 answer
26 views

Speech comparison engine

I need a lightweight, non-cloud library to compare speech samples with words (preferrably for English, French, German, Spanish and pther languages), written in JS or WebAssembly or compiled for JS ...
1 vote
0 answers
20 views

classification of audio notes based on first few seconds

I record audio notes on my recorder, and each belongs to a certain category ("work", "parenting", "miscellaneous", etc.). At the beginning of each recording, I say the name of the category, then stay ...
1 vote
1 answer
56 views

Trainable, high-quality, open-source Speech Recognition package under Windows

For an internal project, I am looking for a Speech Recognition solution that fulfills the following criteria: It needs to be open-source and offline (i.e. not just using cloud based API's) It needs ...
  • 111
1 vote
0 answers
232 views

Offline speech recognition in html/javascript page

I wanted a speech recognition library that works in html page with the help of javascript, and that can be used OFFLINE (in localhost without Internet). (Also I don't want to add words to recognize ...
  • 21
1 vote
0 answers
14 views

I need a software for speech recognition from multiple people and transcription in Arabic

I need a software that is able to recognize several people (possibly 5-10) speaking at the same time and transcribe the audio, also for it to be able to do this for arabic language. IBM Watson is ...
  • 11
1 vote
0 answers
21 views

Audio transcription with word-level time-resolution accuracy

The usual transcription softwares (manual or automated) only give you the time-resolution (not sure if the right word) of one sentence or a group of words at least, for example: 00:00:00,000 --> ...
1 vote
0 answers
19 views

Analyze changes of voice volume (dB) throughout the day

I am looking for a program running on Microsoft Windows that can record and analyze changes of voice volume (dB) throughout the day when I speak to the computer's microphone. Any price, license is ...
1 vote
0 answers
156 views

Speech recognition engine in Dutch

I am currently searching for a speech engine for Dutch. My engine needs to detect keywords only, like: 'stand up', 'say hello', 'walk forward', etc. I have looked up CMU Sphinx4, Dragon Nuance(not ...
  • 11
1 vote
0 answers
49 views

Speech recognition tool for gaming

I'm looking for a speech recognition software for gaming. The goal is to control my computer with my voice by emulating my keyboard or joystick/gamepad. I'm working/playing on Windows 8. The software ...
1 vote
0 answers
21 views

Android application to gather speech recognition statistics

I am looking for an Android application that can gather some statistics on one's use of the Google speech recognition system on Android. E.g. the number of transcribed words with speech recognition ...
0 votes
0 answers
10 views

Program allowing me to use Android's Gboard voice typing (speech recognition) in any program on Windows

I believe that Gboard voice typing (speech recognition) (mirror) on Android outperforms all existing speech recognition programs on Microsoft Windows, such as Dragon Professional Individual and ...
0 votes
0 answers
42 views

Is there any unsupervised speaker diarization tools that works for long files?

I have a lot of mp3 files where different people talk to each other. They are usually 1 hours long. I need to know when which person speaks. The person differ from file to file, so nothing has to be ...
0 votes
0 answers
13 views

Gratis text to speech Windows app which does not need training

I am trying to follow a video tutorial which is simply too fast. I have to pause every 5 seconds to try ot take notes. Is there a gratis text to speech Windows app which does not need training?
0 votes
1 answer
43 views

Voice to text using nodeJS

I need a nodeJS package to convert voice to text. It should support all browsers, be open source and free for enterprise use.
  • 1
0 votes
1 answer
31 views

Use Youtube as speech set for speech recognition data

DNNs are huge data hungry algorithms specially bidirectional-LSTM. For speech recognition models, there's a dearth of voice corpus for specific language/ accents. However, YouTube is a huge library ...
  • 101
0 votes
0 answers
25 views

Suggest for each word I typed alternative words that are pronounced similarly

I am looking for a program running on Microsoft Windows that can suggest for each word I typed alternative words that are pronounced similarly. I'm mostly interested in texts written in English. ...